Digitized intelligent workman service platform and method

Abstract

The invention relates to the technical field of data sharing, and particularly discloses a digital intelligent zero work service platform and method, and the method comprises the steps: transmitting an authority obtaining request to a user when a filing request of the user is received, and receiving the authority granted by the user; performing scene verification on the user, after the verification is passed, counting work information, and generating work experience of the user; determining the integrating degree of the user and each field based on the work experience, matching the user according to the integrating degree when a recruitment demand containing the integrating degree input by a recruiter is received, and establishing a bidirectional interaction channel; the platform verifies the working environment of the worker engaged in the workpiece, after the verification is passed, the keyword corresponding to the current working environment is inquired as the working experience, and the integrating degree of the worker engaged in the workpiece and each field can be determined based on the working experience, so that the working ability of the worker engaged in the workpiece is quantified, and the working efficiency is improved. And job hunting and recruitment are facilitated.

Description

Technical Field

[0001] The present invention relates to the technical field of data sharing, and in particular to a digital intelligent gig service platform and method. Background Art

[0002] Gig workers are workers who sign short-term employment contracts with companies or individual clients, perform various jobs and receive compensation. Legally, they are not formal employees of the company and can work for multiple companies at the same time. Unlike traditional companies, companies that use gig workers no longer rely on internal management systems, wage systems and labor policies to manage these employees.

[0003] For workers engaged in gig work, it is difficult to have clear records of their work experience like that of permanent workers. It is difficult for existing platforms to evaluate their abilities, and it is also difficult for recruiters to know the work abilities of workers engaged in gig work. If the work experience of workers engaged in gig work can be quantified, then an excellent recruitment service platform can be built, which is beneficial for job seekers and recruiters. Summary of the invention

[0004] The purpose of the present invention is to provide a digital intelligent gig service platform and method to solve the problems raised in the above-mentioned background technology.

[0005] To achieve the above object, the present invention provides the following technical solutions:

[0006] A digital intelligent gig service method, the method comprising:

[0007] Upon receiving a user's filing request, sending a permission acquisition request to the user and receiving the permissions granted by the user; the permissions include location sharing permissions and camera application permissions;

[0008] Acquire the user's location based on the location sharing authority, generate a verification instruction according to the user's location, and perform scenario verification on the user;

[0009] When the verification is passed, the work information is counted to generate the user's work experience; the work experience is a set of keywords with time period tags;

[0010] The compatibility between the user and each field is determined based on the work experience. When a recruitment requirement containing the compatibility is received from the recruiter, the user is matched according to the compatibility to establish a two-way interactive channel.

[0011] Furthermore, the step of obtaining the user location based on the location sharing authority, generating a verification instruction according to the user location, and performing scene verification on the user includes:

[0012] Receive the work scene and work period input by the user, and obtain the user's location during the work period based on the location sharing permission granted by the user;

[0013] The user's location is counted based on time to obtain a location representation map; wherein the updating process is to increment a preset value at the location;

[0014] Regularly traverse the position representation diagram to calculate the data density of each point;

[0015] If the data density at the current location meets the preset conditions, a scene verification request is generated to perform scene verification on the user.

[0016] Furthermore, the step of periodically traversing the position representation diagram and calculating the data density of each point includes:

[0017] Read the position representation diagram regularly and convert it into a numerical matrix;

[0018] Traversing the numerical matrix, taking each point as the center, intercepting a preset range, and calculating the data density at the center point based on the numerical value within the preset range; the preset range is a circular range;

[0019] The calculation formula for data density is:

[0020] Where M is the data density at a certain point, R is the radius of the preset range, and Z is θρ is the value at point (θ, ρ) within the preset range, (θ, ρ) is the polar coordinate; S represents the area of ​​the preset range, S = πR 2 .

[0021] Furthermore, if the data density at the current location meets a preset condition, a scene verification request is generated, and the step of performing scene verification on the user includes:

[0022] If the current location meets the preset conditions, a scene verification request is generated;

[0023] Record scene videos based on camera application permissions and convert scene videos into image groups;

[0024] Reading a working scene, reading features from a preset feature library according to the working scene, and traversing images in the image group based on the read features;

[0025] During the traversal process, the similarity between the feature and each area in the image is calculated in real time. When any similarity is greater than the preset threshold, the timestamp of the feature and the corresponding image is recorded;

[0026] The verification is determined based on the recorded features and the timestamp of the corresponding image.

[0027] Furthermore, after the verification is passed, the step of collecting work information and generating the user's work experience also includes:

[0028] When the verification is passed, the work scene and work time input by the user are read;

[0029] Retrieve keywords based on work scenarios, count keywords and their work periods, and update work experience based on work periods.

[0030] Furthermore, the step of determining the compatibility of the user with each field based on the work experience, matching the user according to the compatibility when receiving a recruitment requirement containing the compatibility input by the recruiter, and establishing a two-way interactive channel includes:

[0031] Determine the relevance of each keyword in the work experience to each field based on the large language model;

[0032] Query the time difference between the working period corresponding to each keyword and the current time, and determine the weight according to the time difference; the weight is inversely proportional to the time difference;

[0033] For any field, the relevance between each keyword and the field is accumulated based on the weights to serve as the compatibility between the user and the field;

[0034] Receive the demand fit input by the recruiter, match users based on the demand fit, and establish a two-way interactive channel between the recruiter and the user.

[0035] The technical solution of the present invention also provides a digital intelligent odd-job service platform, which includes:

[0036] The permission acquisition module is used to send a permission acquisition request to the user upon receiving a filing request from the user, and receive the permissions granted by the user; the permissions include location sharing permissions and camera application permissions;

[0037] A scene verification module, used to obtain the user location based on the location sharing authority, generate a verification instruction according to the user location, and perform scene verification on the user;

[0038] A work experience generation module is used to collect work information and generate the user's work experience after the verification is passed; the work experience is a set of keywords containing time period tags;

[0039] The recruitment matching module is used to determine the compatibility of the user with various fields based on the work experience, and when receiving the recruitment requirements containing the compatibility input by the recruiter, match the user according to the compatibility and establish a two-way interactive channel.

[0040] Furthermore, the scenario verification module includes:

[0041] A user location acquisition unit, used to receive a work scene and work period input by a user, and acquire the user's location within the work period based on the location sharing authority granted by the user;

[0042] A location statistics unit, used to count user locations based on time to obtain a location representation map; wherein the updating process is to increment a preset value at the location;

[0043] A numerical verification unit, used for periodically traversing the position representation diagram and calculating the data density of each point;

[0044] The verification execution unit is used to generate a scene verification request and perform scene verification on the user if the data density at the current location meets a preset condition.

[0045] Furthermore, the work experience generation module includes:

[0046] A data reading unit, used to read the work scene and work period input by the user after the verification is passed;

[0047] The experience updating unit is used to retrieve keywords based on work scenarios, count keywords and their work periods, and update work experience based on work periods.

[0048] Furthermore, the recruitment matching module includes:

[0049] A relevance determination unit, used to determine the relevance between each keyword and each field in the work experience based on the large language model;

[0050] A weight determination unit, used to query the time difference between the working period corresponding to each keyword and the current time, and determine the weight according to the time difference; the weight is inversely proportional to the time difference;

[0051] A compatibility calculation unit, for accumulating the relevance of each keyword with the field based on the weights for any field as the compatibility between the user and the field;

[0052] The channel establishment unit is used to receive the demand fit input by the recruiter, match users based on the demand fit, and establish a two-way interactive channel between the recruiter and the user.

[0053] Compared with the prior art, the beneficial effects of the present invention are: this platform receives registration requests uploaded by workers engaged in odd jobs, analyzes their locations, and then verifies the work environment. When the verification is passed, the keywords corresponding to the current work environment are queried as work experience. Then, based on the work experience, the degree of fit between the workers engaged in odd jobs and various fields can be determined, thereby quantifying the work ability of the workers engaged in odd jobs, which is convenient for job hunting and recruitment. BRIEF DESCRIPTION OF THE DRAWINGS

[0054] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings in the following description are only some embodiments of the present invention.

[0055] Figure 1 A flowchart of the digital smart gig service approach.

[0056] Figure 2 This is the structural diagram of the digital intelligent gig service platform. DETAILED DESCRIPTION

[0057] For gig workers, their work experience is difficult to have clear records like that of permanent workers. It is difficult for existing platforms to evaluate their abilities, and it is also difficult for employers to know the work abilities of gig workers.

[0058] In order to make the technical problems, technical solutions and beneficial effects to be solved by the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0059] Figure 1 The flowchart of the digital intelligent gig service method is as follows. In an embodiment of the present invention, a digital intelligent gig service method is provided, and the method includes:

[0060] Step S100: upon receiving a user's filing request, sending a permission acquisition request to the user, and receiving permissions granted by the user; the permissions include location sharing permissions and camera application permissions;

[0061] The users targeted by the technical solution of the present invention are generally job seekers. When using this platform, users will register. After registration, users will have a dedicated account. In the daily work stage, users will record their work experience. For odd jobs, there is no definite work cycle, and the traditional contract-based registration method is adopted, which has low flexibility. The platform provided by this application provides a registration method. When receiving the user's registration request, the user's current work is registered, and finally a work experience reflecting the user's odd job work process is obtained, which is convenient for recruiters to recruit, thereby building a data sharing platform.

[0062] In the technical solution of the present invention, when creating work experience, it is necessary to obtain the user's location and the user's scene. When filing, the user enters the work scene, and then the platform will verify it. The verification requires considering two parameters: the user's location and the user's scene. Therefore, it is necessary to obtain the following permissions, send a permission acquisition request to the user, and receive the permissions granted by the user.

[0063] Step S200: obtaining the user location based on the location sharing authority, generating a verification instruction according to the user location, and performing scenario verification on the user;

[0064] After obtaining the location sharing permission, the user location is obtained based on the location sharing permission, and the user's work status is preliminarily verified based on the user location to determine whether the user is working in the designated area. If the user is working in the designated area, further scene verification is performed.

[0065] Step S300: After the verification is passed, the work information is counted to generate the user's work experience; the work experience is a set of keywords with time period tags;

[0066] When the verification is passed, it means that the registered information entered by the user is true. At this time, all the real work information is counted to generate work experience. The work experience is a set of keywords with time period labels, that is, which keywords are in which time period.

[0067] Step S400: determining the compatibility of the user with each field based on the work experience, and upon receiving a recruitment requirement containing the compatibility input by the recruiter, matching the user according to the compatibility, and establishing a two-way interactive channel;

[0068] After the work experience is generated, it shows what work the user did in what time period, and all of them are represented by keywords. By identifying these keywords, it can be determined which fields each keyword is more suitable for, which is represented by the parameter of fit. When a recruitment demand containing fit is received from the recruiter, the user is matched according to the fit and a two-way interactive channel is established.

[0069] It is worth mentioning that, from a conventional perspective, every recruiter wants to recruit users with 100% fit, but in fact, the higher the fit, the higher the salary. Taking all factors into consideration, the needs of different recruiters may be different.

[0070] Regarding step S200, the steps of obtaining the user location based on the location sharing authority, generating a verification instruction according to the user location, and performing scene verification on the user include:

[0071] Receive the work scene and work period input by the user, and obtain the user's location during the work period based on the location sharing permission granted by the user;

[0072] The user's location is counted based on time to obtain a location representation map; wherein the updating process is to increment a preset value at the location;

[0073] Regularly traverse the position representation diagram to calculate the data density of each point;

[0074] If the data density at the current location meets the preset conditions, a scene verification request is generated to perform scene verification on the user.

[0075] In an example of the technical solution of the present invention, a work scene and a work period input by a user are received, the input work scene and work period indicate where the user works and when the corresponding work period is, the user location is obtained based on the location sharing authority granted by the user during the work period, the user location is counted based on time, and a location representation graph is obtained, the location representation graph indicates the locations where the user appears, and by analyzing the location representation graph, it can be determined at which location a scene verification request is generated, and then the scene verification is performed on the user.

[0076] The position display diagram is described as follows:

[0077] After obtaining the location, mark the corresponding point on the map, increase the value of the point by 1, and repeat this process continuously. The values ​​of each point will continue to increase, and eventually a map of the user's historical location will be obtained, called a location representation map. The value at each location represents the length of time the user stays at different locations.

[0078] Furthermore, the step of periodically traversing the position representation diagram and calculating the data density of each point includes:

[0079] Read the position representation diagram regularly and convert it into a numerical matrix;

[0080] The numerical matrix is ​​traversed, a preset range is intercepted with each point as the center, and the data density at the center point is calculated based on the numerical value within the preset range; the preset range is a circular range.

[0081] The position representation diagram is read regularly. The position representation diagram itself is an image, which is two-dimensional data. It is essentially a matrix. The process of converting it into a numerical matrix is ​​very simple. Each row and column position is traversed to calculate the data density and data concentration. The data density represents the length of time the user stays near the row and column position (preset range) with the row and column position as the center. The calculation process of the data density is as follows:

[0082] Where M is the data density at a certain point, R is the radius of the preset range, and Z is θρ is the value at point (θ, ρ) within the preset range, (θ, ρ) is the polar coordinate; S represents the area of ​​the preset range, S = πR 2 .

[0083] The meaning of the location verification process is that only when the user frequently appears within a certain range can he be considered to be working seriously. At this time, the subsequent video verification will be triggered. The location and video actually construct a two-level verification scheme. The location recognition process is used to trigger the video recognition process. Since the video recognition process consumes more resources, this multi-level verification scheme can improve resource utilization.

[0084] Regarding the scene verification process, if the data density at the current location meets the preset conditions, a scene verification request is generated, and the steps of performing scene verification on the user include:

[0085] If the current location meets the preset conditions, a scene verification request is generated;

[0086] Record scene videos based on camera application permissions and convert scene videos into image groups;

[0087] Reading a working scene, reading features from a preset feature library according to the working scene, and traversing images in the image group based on the read features;

[0088] During the traversal process, the similarity between the feature and each area in the image is calculated in real time. When any similarity is greater than the preset threshold, the timestamp of the feature and the corresponding image is recorded;

[0089] The verification is determined based on the recorded features and the timestamp of the corresponding image.

[0090] In an example of the technical solution of the present invention, if the current location meets the preset conditions, a scene verification request is generated. Based on the camera application permissions granted in advance by the user, the environment in which the current user is located can be recorded to obtain a scene video. By removing the audio from the scene video, an image group can be obtained. Then, the work scene is read. The work scene is the environment in which the user works. For odd jobs, the types of environments are limited, and the scene features that may exist in each environment can also be counted. The pre-counted scene features are stored in a feature library.

[0091] In actual application, the working scene is read, and features are read from a preset feature library according to the working scene. The images in the image group are traversed based on the read features. The traversal process is comparison recognition. The meaning of comparison recognition is to calculate the similarity between the feature and each sub-region in the image. If the similarity is high enough, it is considered to be matched, that is, the feature appears in the corresponding frame image, and the match is determined to be successful.

[0092] After each feature is traversed, the verification is successful based on which features are successfully matched with the image and how many frames each feature is successfully matched in. Combining these two parameters, it can be determined whether the verification is successful.

[0093] In an example of the technical solution of the present invention, one of the conditions for determining whether the verification is successful is that, for a certain feature, an image quantity threshold is set. When the number of image frames corresponding to the feature (determined by the timestamp) reaches the image quantity threshold, the feature is marked as a valid feature, the number of valid features is recorded, and then a feature quantity threshold is set. When the number of valid features reaches the feature quantity threshold, it is determined that the verification is successful.

[0094] Regarding step S300, after the verification is passed, the step of collecting work information and generating the user's work experience also includes:

[0095] When the verification is passed, the work scene and work time input by the user are read;

[0096] Retrieve keywords based on work scenarios, count keywords and their work periods, and update work experience based on work periods.

[0097] After the verification is passed, the work scene and work period entered by the user are read, and keywords are retrieved based on the work scene. This keyword refers to the field corresponding to the work scene, such as chemical, petroleum, and construction, etc.; each work scene can query some keywords, and each work scene also corresponds to a work period. All keywords are counted based on the work period to obtain work experience.

[0098] Regarding step S400, the steps of determining the compatibility between the user and each field based on the work experience, matching the user according to the compatibility when receiving a recruitment demand containing the compatibility input by the recruiter, and establishing a two-way interactive channel include:

[0099] Determine the relevance of each keyword in the work experience to each field based on the large language model;

[0100] Query the time difference between the working period corresponding to each keyword and the current time, and determine the weight according to the time difference; the weight is inversely proportional to the time difference;

[0101] For any field, the relevance between each keyword and the field is accumulated based on the weights to serve as the compatibility between the user and the field;

[0102] Receive the demand fit input by the recruiter, match users based on the demand fit, and establish a two-way interactive channel between the recruiter and the user.

[0103] For any user, the correlation between each keyword and each field in the work experience is determined based on the large language model. For example, using a conventional word vector model, words with stronger correlation generally have closer vectors, and the process of obtaining the correlation is very simple; then, the time difference between the working period corresponding to each keyword and the current moment is queried. The earlier the work experience (keyword), the smaller the weight. The product of the weight and the keyword is calculated and then accumulated to obtain the fit between the user and the field; the practical significance of this process is that for any field, keywords related to the field are queried in the user's work experience, and the correlation of the corresponding keywords is read. The more recent the work experience, the higher the weight. The fit can be obtained by accumulating the correlation of the queried keywords based on the weight.

[0104] Finally, the platform receives the demand fit input by the recruiter, matches users based on the demand fit, and establishes a two-way interactive channel between the recruiter and the user. In actual applications, when the recruiter inputs the demand fit, the platform will generally feedback a salary level. If the salary level is unacceptable to the recruiter, the demand fit will be lowered at this time to match more users, and accordingly, the salary level will also be lowered.

[0105] Figure 2 : is a structural diagram of a digital intelligent gig service platform. In an embodiment of the present invention, a digital intelligent gig service platform, the platform 10 includes:

[0106] The permission acquisition module 11 is used to send a permission acquisition request to the user upon receiving a filing request from the user, and receive the permissions granted by the user; the permissions include location sharing permissions and camera application permissions;

[0107] A scene verification module 12, used to obtain a user location based on a location sharing authority, generate a verification instruction according to the user location, and perform scene verification on the user;

[0108] The work experience generation module 13 is used to collect work information and generate the user's work experience after the verification is passed; the work experience is a set of keywords containing time period tags;

[0109] The recruitment matching module 14 is used to determine the compatibility of the user with each field based on the work experience, and when receiving a recruitment demand containing the compatibility input by the recruiter, match the user according to the compatibility and establish a two-way interactive channel.

[0110] Furthermore, the scene verification module 12 includes:

[0111] A user location acquisition unit, used to receive a work scene and work period input by a user, and acquire the user's location within the work period based on the location sharing authority granted by the user;

[0112] A location statistics unit, used to count user locations based on time to obtain a location representation map; wherein the updating process is to increment a preset value at the location;

[0113] A numerical verification unit, used for periodically traversing the position representation diagram and calculating the data density of each point;

[0114] The verification execution unit is used to generate a scene verification request and perform scene verification on the user if the data density at the current location meets a preset condition.

[0115] Specifically, the work experience generating module 13 includes:

[0116] A data reading unit, used to read the work scene and work period input by the user after the verification is passed;

[0117] The experience updating unit is used to retrieve keywords based on work scenarios, count keywords and their work periods, and update work experience based on work periods.

[0118] Furthermore, the recruitment matching module 14 includes:

[0119] A relevance determination unit, used to determine the relevance between each keyword and each field in the work experience based on the large language model;

[0120] A weight determination unit, used to query the time difference between the working period corresponding to each keyword and the current time, and determine the weight according to the time difference; the weight is inversely proportional to the time difference;

[0121] A compatibility calculation unit, for accumulating the relevance of each keyword with the field based on the weights for any field as the compatibility between the user and the field;

[0122] The channel establishment unit is used to receive the demand fit input by the recruiter, match users based on the demand fit, and establish a two-way interactive channel between the recruiter and the user.

[0123] The above technical solution provides an intelligent service platform, which is usually applied in the form of an App, and its functions are as follows:

[0124] This platform receives registration requests uploaded by workers engaged in gig work, analyzes their location, and then verifies the work environment. Once the verification is passed, the platform queries the keywords corresponding to the current work environment as work experience. Then, based on the work experience, the compatibility of the workers engaged in gig work with various fields can be determined, thereby quantifying the work ability of the workers engaged in gig work, which is convenient for both job hunting and recruitment.

[0125] Through the specific description of the above embodiments, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, it can also be implemented by hardware. Based on such an understanding, the above technical solution can be essentially or partly contributed to the prior art in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, and the storage medium includes a read-only memory (ROM), a random access memory (RAM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), a one-time programmable read-only memory (OTPROM), an electronically erasable rewritable read-only memory (EEPROM), a compact disc (CD-ROM) or other optical disc storage, a magnetic disk storage, a magnetic tape storage, or any other computer-readable medium that can be used to carry or store data.

[0126] Finally, it should be noted that the digital intelligent gig service platform and method disclosed in the embodiments of the present invention only disclose the preferred embodiments of the present invention, which are only used to illustrate the technical solution of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A digital intelligent gig service method, characterized in that: The method comprises: Upon receiving a user's filing request, sending a permission acquisition request to the user and receiving the permissions granted by the user; the permissions include location sharing permissions and camera application permissions; Acquire the user's location based on the location sharing authority, generate a verification instruction according to the user's location, and perform scenario verification on the user; When the verification is passed, the work information is counted to generate the user's work experience; the work experience is a set of keywords with time period tags; The compatibility between the user and each field is determined based on the work experience. When a recruitment requirement containing the compatibility is received from the recruiter, the user is matched according to the compatibility to establish a two-way interactive channel.

2. The digital intelligent gig service method according to claim 1, characterized in that: The steps of obtaining the user location based on the location sharing authority, generating a verification instruction according to the user location, and performing scene verification on the user include: Receive the work scene and work period input by the user, and obtain the user's location during the work period based on the location sharing permission granted by the user; The user's location is counted based on time to obtain a location representation map; wherein the updating process is to increment a preset value at the location; Regularly traverse the position representation diagram to calculate the data density of each point; If the data density at the current location meets the preset conditions, a scene verification request is generated to perform scene verification on the user.

3. The digital intelligent gig service method according to claim 2, characterized in that: The step of periodically traversing the position representation diagram and calculating the data density of each point comprises: Read the position representation diagram regularly and convert it into a numerical matrix; Traversing the numerical matrix, taking each point as the center, intercepting a preset range, and calculating the data density at the center point based on the numerical value within the preset range; the preset range is a circular range; The calculation formula for data density is: Where M is the data density at a certain point, R is the radius of the preset range, and Z is θρ is the value at point (θ, ρ) within the preset range, (θ, ρ) is the polar coordinate; S represents the area of ​​the preset range, S = πR 2 .

4. The digital intelligent gig service method according to claim 2, characterized in that: If the data density at the current location meets the preset conditions, a scene verification request is generated, and the step of performing scene verification on the user includes: If the current location meets the preset conditions, a scene verification request is generated; Record scene videos based on camera application permissions and convert scene videos into image groups; Reading a working scene, reading features from a preset feature library according to the working scene, and traversing images in the image group based on the read features; During the traversal process, the similarity between the feature and each area in the image is calculated in real time. When any similarity is greater than the preset threshold, the timestamp of the feature and the corresponding image is recorded; The verification is determined based on the recorded features and the timestamp of the corresponding image.

5. The digital intelligent gig service method according to claim 2, characterized in that: After the verification is passed, the step of collecting work information and generating the user's work experience also includes: When the verification is passed, the work scene and work time input by the user are read; Retrieve keywords based on work scenarios, count keywords and their work periods, and update work experience based on work periods.

6. The digital intelligent gig service method according to claim 1, characterized in that: The step of determining the compatibility between the user and each field based on the work experience, matching the user according to the compatibility when receiving a recruitment demand containing the compatibility input by the recruiter, and establishing a two-way interactive channel includes: Determine the relevance of each keyword in the work experience to each field based on the large language model; Query the time difference between the working period corresponding to each keyword and the current time, and determine the weight according to the time difference; the weight is inversely proportional to the time difference; For any field, the relevance between each keyword and the field is accumulated based on the weights to serve as the compatibility between the user and the field; Receive the demand fit input by the recruiter, match users based on the demand fit, and establish a two-way interactive channel between the recruiter and the user.

7. A digital intelligent gig service platform, characterized in that: The platform includes: The permission acquisition module is used to send a permission acquisition request to the user upon receiving a filing request from the user, and receive the permissions granted by the user; the permissions include location sharing permissions and camera application permissions; A scene verification module, used to obtain the user location based on the location sharing authority, generate a verification instruction according to the user location, and perform scene verification on the user; A work experience generation module is used to collect work information and generate the user's work experience after the verification is passed; the work experience is a set of keywords containing time period tags; The recruitment matching module is used to determine the compatibility of the user with various fields based on the work experience, and when receiving the recruitment requirements containing the compatibility input by the recruiter, match the user according to the compatibility and establish a two-way interactive channel.

8. The digital intelligent gig service platform according to claim 7, characterized in that: The scenario verification module includes: A user location acquisition unit, used to receive a work scene and work period input by a user, and acquire the user's location within the work period based on the location sharing authority granted by the user; A location statistics unit, used to count user locations based on time to obtain a location representation map; wherein the updating process is to increment a preset value at the location; A numerical verification unit, used for periodically traversing the position representation diagram and calculating the data density of each point; The verification execution unit is used to generate a scene verification request and perform scene verification on the user if the data density at the current location meets a preset condition.

9. The digital intelligent gig service platform according to claim 8, characterized in that: The work experience generation module includes: A data reading unit, used to read the work scene and work period input by the user after the verification is passed; The experience updating unit is used to retrieve keywords based on work scenarios, count keywords and their work periods, and update work experience based on work periods.

10. The digital intelligent gig service platform according to claim 8, characterized in that: The recruitment matching module includes: A relevance determination unit, used to determine the relevance between each keyword and each field in the work experience based on the large language model; A weight determination unit, used to query the time difference between the working period corresponding to each keyword and the current time, and determine the weight according to the time difference; the weight is inversely proportional to the time difference; A compatibility calculation unit, for accumulating the relevance of each keyword with the field based on the weights for any field as the compatibility between the user and the field; The channel establishment unit is used to receive the demand fit input by the recruiter, match users based on the demand fit, and establish a two-way interactive channel between the recruiter and the user.

Images