Buyer-provider matching algorithm

Description

FIELD OF THE INVENTION

The present invention relates to matching algorithms. More particularly, the present invention relates to a buyer-provider matching algorithm.

BACKGROUND OF THE INVENTION

Many job sites that provide a community for job providers and job seekers contain a wealth of resources for both the job providers and the job seekers. However, prior art job sites suffer from a number of shortcomings. For example, a job site that returns a provider search result listing job seekers alphabetically by name presents an inconvenience for a job provider, because the provider search result has insignificant value in terms of finding a qualified job seeker. The provider search result listing job seekers based only on a keyword match also presents an inconvenience for the job provider, because the provider search result does not take into consideration of other important attributes, such as how well a job seeker is regarded in the community. For example, the job seeker having a proper education and qualifications may not work well with others or may not have good work ethics. The provider search result based only on the keyword match do not reflect such attributes. As such, the ability to organize data properly and return the data in a significant manner is important.

The present invention addresses at least these limitations in the prior art.

SUMMARY OF THE INVENTION

An object of the present invention is to provide a buyer-provider matching algorithm within a services exchange medium. In the services exchange medium, buyers find and hire service providers “on demand” to get projects done quickly and cost effectively.

In one aspect, a computerized method of generating a provider results list comprises calculating a provider search score for each service provider within a services exchange medium and sorting the provider results list based on the provider search score. The provider search score is a sum of at least one provider match score enhanced by a reputation score. The provider search score is stored on a computing device. The reputation score in some embodiments is dependent on at least one of customer satisfaction, earnings, and participation by a service provider within the services exchange medium. A provider match score in some embodiments is based on at least one of match between a search text and a section of a profile, and match between a the search text and a part of a project completed by the service provider. In some embodiments, the section of the profile is a provider tagline section, a provider user ID section, a provider name section, a summary services description section, a keywords section, a skills section, an about us section, a detailed services exchange section, a credentials section, or an experience section. A number of points for a match between the search text and the section of the profile comprises a first hit value and a total secondary hit score. The calculating comprises adjusting the total secondary hit score by a secondary hits magnifier. The secondary hits magnifier is modifiable. The calculating further comprises adding the first hit value and the total secondary hit score together, and multiplying an absolute weight to a sum of the first hit value and the total secondary hit score. The absolute weight is modifiable. In some embodiments, the part of the project is a project name or a project description. A number of points associated with a match between the search text and the project name is modifiable. A number of points associated with a match between the search text and the project description is modifiable.

In another aspect, a provider search method within a services exchange medium comprises obtaining a search text, calculating a first score based on a reputation of a service provider, computing a plurality of second scores based on matches between the search text and service provider data, determining a third score based on the plurality of second scores enhanced by the first score, wherein the third score is stored on a computing device, repeating steps calculating, computing, determining for all service providers within the services exchange medium, and generating a provider results list. Typically, the provider results list is sorted by the third score. The reputation in some embodiments is dependent on at least one of customer satisfaction, earnings, and participation by the service provider within the services exchange medium. The method in some embodiments further comprises comparing the search text with sections of a profile belonging to the service provider, and checking the search text against parts of an at least one project completed by the service provider. The sections include provider tagline section, a provider user ID section, a provider name section, a summary services description section, a keywords section, a skills section, an about us section, a detailed services exchange section, a credentials section, and an experience section. The parts include a project name and a project description. A number of points for a match between the search text and a section of the profile comprises a first hit value and a total secondary hit score. The comparing comprises adjusting the total secondary hit score by a secondary hits magnifier. The secondary hits magnifier is modifiable. The comparing further comprises adding the first hit score and the total secondary hit score together, and multiplying an absolute weight to a sum of the first hit value and the total secondary hit score. The absolute weight is modifiable. A number of points for a match frequency between the search text and the project name is modifiable. A score for a match frequency between the search text and the project description is modifiable.

Yet, in another aspect, a system for creating portable interactive windows comprises a processor and an application executed by the processor. The application is for calculating a provider search score for each service provider within a services exchange medium and sorting the provider results list based on the provider search score. The provider search score is a sum of at least one provider match score enhanced by a reputation score. The reputation score in some embodiments is dependent on at least one of customer satisfaction, earnings, and participation by a service provider within the services exchange medium. A provider match score in some embodiments is based on at least one of match between a search text and a section of a profile, and match between a the search text and a part of a project completed by the service provider. In some embodiments, the section of the profile is a provider tagline section, a provider user ID section, a provider name section, a summary services description section, a keywords section, a skills section, an about us section, a detailed services exchange section, a credentials section, or an experience section. A number of points for a match between the search text and the section of the profile comprises a first hit value and a total secondary hit score. The calculating comprises adjusting the total secondary hit score by a secondary hits magnifier. The secondary hits magnifier is modifiable. The calculating further comprises adding the first hit value and the total secondary hit score together, and multiplying an absolute weight to a sum of the first hit value and the total secondary hit score. The absolute weight is modifiable. In some embodiments, the part of the project is a project name or a project description. A number of points associated with a match between the search text and the project name is modifiable. A number of points associated with a match between the search text and the project description is modifiable.

Yet, in another aspect, a computerized method of enhancing provider match scores comprises determining a first match score for each section of a profile stored on a computing device, determining a second match score based on a number of matches between a search text and a project title of each project completed by a service provider, and determining a third match score based on a number of matches between the search text and a project description of each project completed by the service provider. The method also includes adding together first match scores, the second match score, and the third match score to obtain a total match score. The method further includes multiplying an enhancement value to the total match score, the enhancement value is dependent on reputation of the service provider

BRIEF DESCRIPTION OF THE DRAWINGS

FIG. 1 illustrates a table of exemplary sections of a profile in accordance with some embodiments of the present invention.

FIG. 2 illustrates a table of project name match frequencies and corresponding score values in accordance with some embodiments of the present invention.

FIG. 3 illustrates a table of project description match frequencies and corresponding score values in accordance with some embodiments of the present invention.

FIG. 4 illustrates a table of steps to derive a Provider Match score in accordance with some embodiments of the present invention.

FIG. 5 illustrates an exemplary provider results list in accordance with some embodiments of the present invention.

FIG. 6 illustrates a method of providing the returned provider results list in accordance with some embodiments of the present invention.

FIG. 7 illustrates a graphical representation of an exemplary computing device in accordance with some embodiments of the present invention.

DETAILED DESCRIPTION OF THE INVENTION

In the following description, numerous details are set forth for purposes of explanation. However, one of ordinary skill in the art will realize that the invention may be practiced without the use of these specific details. Thus, the present invention is not intended to be limited to the embodiments shown but is to be accorded the widest scope consistent with the principles and features described herein or with equivalent alternatives.

Reference will now be made in detail to implementations of the present invention as illustrated in the accompanying drawings. The same reference indicators will be used throughout the drawings and the following detailed description to refer to the same or like parts.

Embodiments of the present invention are directed to a buyer-provider matching algorithm within a services exchange medium. Preferably, in a services exchange medium, buyers are able to post projects and to search and hire service providers “on demand” to get the projects done quickly and cost effectively. In the services exchange medium, a service provider creates a profile in order to be immediately connected to a buyer looking for the service provider's expertise. Typically, the service provider's profile describes the service provider's professional abilities. The buyer is able to review the service provider's profile to make an instant hiring decision.

The buyer-provider matching algorithm in some embodiments calculates a “Provider Search” score for each service provider within the services exchange medium. A provide results list generated from a provider search is sorted by the “Provider Search” score. In some embodiments, the buyer-provider matching algorithm preferably uses two scores to calculate the “Provider Search” score: a “Reputation” score and a “Provider Match” score. Each, in turn, is described below.

The “Reputation” score is a quantitative metric which represents the service provider's reputation within the services exchange medium. In some embodiments, the “Reputation” score is dependent on factors such as customer satisfaction, earnings, and/or participation by the service provider within the services exchange medium. Other factors are possible. The “Reputation” score typically ranges from 0% to 100%. If the service provider's “Reputation” score is 11%, then the service provider's reputation is better than 11% of other service providers within the services exchange medium. If the service provider's “Reputation” score is 100%, then the service provider's reputation is better than all other service providers within the services exchange medium. In other embodiments, the “Reputation” score is configured to enhance the “Provider Match” score.

As mentioned above, the buyer-provider matching algorithm also uses the “Provider Match” score to calculate the “Provider Search” score. In some embodiments, if a search text is entered as part of the provider search, then the search text is compared against the service provider's profile and against past projects completed by the service provider within the services exchange medium. In this discussion, assume that the search text is “php.”

FIG. 1 illustrates a table 100 of exemplary sections of a profile in accordance with the present invention. In some embodiments, the “php” search text is compared against different sections of the profile. Each section is associated with an absolute weight, which is variable and adjustable. The absolute weight typically ranges from 0 to 100. In some embodiments, the absolute weight are determined by the services exchange medium. As shown in an “Absolute Weight” column 160, a “Provider Tagline” section 105 has an absolute weight of 100, a “Provider User ID” section 110 has an absolute weight of 15, a “Provider Name” section 115 has an absolute weight of 75, a “Summary Service Description” section 120 has an absolute weight of 75, a “Service Tags/Keywords” section 125 has an absolute weight of 75, a “Skills” section 130 has an absolute weight of 75, an “About Us” (e.g. introduction) section 135 has an absolute weight of 25, a “Detailed Service Description” section 140 has an absolute weight of 50, a “Provider Credentials” section 145 has an absolute weight of 25, an “Experience” section 150 has an absolute weight of 25, and a “Provider Primary Location” section 155 has an absolute weight of 0. Other sections of the profile and absolute weights that make up the “Provider Match” score are possible. In some embodiments, a distinction is made between certified skills and uncertified skills. Certified skills typically have a higher absolute weight than uncertified skills.

A “First Hit” column 165 indicates whether a match between the “php” search text and a corresponding section of the profile has occurred during the provider search. Specifically, once the “php” search text is found in that section, a first hit for that section is a one; otherwise, if the section does not contain the “php” search text, then the first hit for that section remains a zero. As illustrated in FIG. 1, a first hit for the “Provider Tagline” 105 is a one, a first hit for the “Service Tags/Keywords” section 125 is a one, and a first hit for the “Detailed Service Description” 140 is a one, because the “php” search text is found in those section. In some embodiments, each section also has a secondary hit magnifier shown in a “Secondary Hits Magnifier” column 170. The secondary hit magnifier, which is variable and adjustable, is used to increase the service provider's “Provider Match” score when the “php” search text is found more than once in that corresponding section. Specifically, a number of secondary hits for that section, shown in a “Secondary N Hits Count” column 175, is multiplied with that section's secondary hits magnifier to get a total secondary hit score, shown in a “Total Secondary Hit Score” column 180. In some embodiments, the secondary hits magnifier values are determined by the services exchange medium.

As illustrated in FIG. 1, the secondary hits magnifier for each section is set to zero, although the secondary hit magnifier values for the sections are able to be set to any and/or different values. As such, regardless how often the “php” search text appears in, for example, the “Detailed Service Description” section 140 more than once, the corresponding total secondary hit score is zero. A total score for each section, shown in a “Total Score” column 185, is determined by adding together the corresponding total secondary hit score and the first hit. The total score for each section is then multiplied with the corresponding absolute weight to determine a calculated weight, shown in a “Calculated Weight” column 190. A total calculated weight 195 is determined by adding together the calculated weight for each section. The total calculated weight 195 is 225. It should be apparent that the table values as illustrated are exemplary only and do not limit the scope of the invention.

In some embodiments, the “php” search text is also compared against past projects completed by the service provider within the services exchange medium. Specifically, the “php” search text is compared against project names of X most recently completed projects within the services exchange medium in the past Z months. And, the “php” search text is compared against project descriptions of Y most recently completed projects within the services exchange medium in the past Z months. Typically, a value of X is 20, a value of Y is 10, and a value of Z is six. Other values of X, Y and Z are possible.

FIG. 2 illustrates a table 200 of project name match frequencies and corresponding scores in accordance with the present invention. The project name match frequencies are shown in a “Frequencies” column 205, and the corresponding scores are shown in a “Score” column 210. The more project name matches that occur during the provider search, a higher score is added to the service provider's “Provider Match” score. For example, the service provider is awarded with a score of 100 if the service provider, within the last six months, has completed one project having the “php” search text as part of the project name. The service provider is awarded a maximum score of 1050 if the service provider, within the last six months, has completed at least 20 projects having the “php” search text as part of the project names. The project name match frequencies and corresponding scores are variable and adjustable. Other project name match frequencies and corresponding scores that make up the “Provider Match” score are possible.

FIG. 3 illustrates a table 300 of project description match frequencies and corresponding scores in accordance with the present invention. The project description match frequencies are shown in a “Frequencies” column 305, and the corresponding scores are shown in a “Score” column 310. The more project description matches that occur during the provider search, a higher score is added to the service provider's “Provider Match” score. For example, the service provider is awarded with a score of 50 if the service provider, within the last six months, has completed one project having the “php” search text as part of the project description. The service provider is awarded a maximum score of 275 if the service provider, within the last six months, has completed at least 10 projects having the “php” search text as part of the project descriptions. The project description match frequencies and corresponding scores are variable and adjustable. Other project description match frequencies and corresponding scores that make up the “Provider Match” score are possible.

FIG. 4 illustrates a table 400 of steps to derive the “Provider Match” score in accordance with the present invention. For example, assume that the service provider's “Reputation” score is 11%. Since the “Reputation” score is used to enhance the “Provider Match” score, an “E Score” multiplier 425 is 1.11. However, if the service provider had a perfect “Reputation” score of 100%, then the “E Score” multiplier 425 is 2, which is in some embodiments the maximum multiplier.

As illustrated in FIG. 4, the “php” search text is found in the following areas: three times in the “Detailed Service Description” section 140 of the profile, one time in the “Service Tags/Keywords” section 125 of the profile, one time in the “Provider Tagline” section 105 of the profile, five times in project descriptions 405 of projects completed within the past six months, and eight times in project names 410 of the projects completed within the past six months. As such, points 420 received for the “Detailed Service Description,” the “Service Tags/Keywords,” the “Provider Tagline,” the “Past Project Description,” and the “Past Project Name” are 50, 75, 100, 200, and 660, respectively. The points 420 are based on the frequencies 415 of the “php” search text found in each of the different areas, referencing the “Calculated Weight” column 190 of FIG. 1, and the “Score” columns 210 and 310 of FIGS. 2-3, respectively. Each of the points 420 received is multiplied with the “E Score” multiplier 425 (e.g. 1.11). As such, the “Reputation” score is configured to enhance the “Provider Match” score. Final scores 430 received for the “Detailed Service Description,” the “Service Tags/Keywords,” the “Provider Tagline,” the “Past Project Description,” and the “Past Project Name” are 55.5, 83.25, 111, 222, and 732.6, respectively. A total final score 435 is determined by adding together the final score for each area. The total final score 435 is 1204 (rounded from 1204.35). In some embodiments, the total final score 435 is the “Provider Search” score.

As mentioned above, the provider results list is sorted by the “Provider Search” score. Since reputation is an important attribute when searching for a qualified service provider, the “Provider Search” score takes into consideration the “Reputation” score. As such, the provider results list is advantageously sorted in a significant manner useful to the buyer searching for a qualified service provider. In some embodiments, the “Provider Search” score also takes into the service provider's performance within the services exchange medium.

FIG. 5 illustrates an exemplary provider results list 500 in accordance with the present invention. In some embodiments, the provider results list 500 is sorted by the “Provider Search” score. As illustrated in FIG. 5, the service provider with the “Provider Search” score of 1204, as calculated above, is MechTechnologies. Bhatia Systems ranks higher than MechTechnologies in the provider results list 500 because Bhatia System has a higher “Provider Search” score than MechTechnologies. Bhatia Systems has a “Provider Search” score of 1, 264. In other embodiments, result rankings 505 and “Provider Search” scores 510 are not shown in the provider results list 500. Yet, in other embodiments, if no search text is entered as part of the provider search, then the “Reputation” score of each service provider is the final determiner of rank. As such, the provider results list 500 is sorted by the “Reputation” score.

FIG. 6 illustrates a process 600 of providing the provider results list in accordance with the present invention. At step 605, the buyer-provider matching algorithm obtains a search text (e.g. “php”) entered by a user. At step 610, the buyer-provider matching algorithm calculates a first score for a service provider within the services exchange medium. Typically, the first score is the “Reputation” score described above. At step 615, the buyer-provider matching algorithm computes a plurality of second scores. Typically, the plurality of second scores is computed by comparing the search text with the service provider's profile and with the past projects completed by the service provider within the services exchange medium. The plurality of second scores is the “Provider Match” score described score. At step 620, the buyer-provider matching algorithm determines a third score. Typically, the third score is derived by using the first score and the plurality of second scores. The third score is the “Provider Search” score described above. Step 625 determines whether a third score has been determined for each service provider within the services exchange medium. If a third score has been determined for each service provider within the services exchange medium, then at step 630, a provider results list is generated and is sorted by the third score. The process 600 ends. Alternatively, a first score is calculated for another service provider at step 610 and the process 600 continues.

The steps of the present invention are embodied in machine-executable instructions. These instructions can be used to cause a general-purpose or special-purpose processor that is programmed with the instructions to perform the steps of the present invention. Alternatively, the steps of the present invention can be performed by specific hardware components that contain hardwired logic for performing the steps, or by any combination of programmed computer components and custom hardware components.

In some embodiments, the present invention is provided as a computing device. FIG. 7 illustrates a graphical representation of an exemplary computing device 700 in accordance with the present invention. The computing device 700, such as a server stores, serves, computes, communicates, generates and/or displays information about the service provider within the services exchange medium. The service provider uses an Internet-ready device, such as a personal computer, to interact with the computer device 700 to create the profile and to generate the online professional badge. In general, a hardware structure suitable for implementing the computing device 700 includes a network interface 702, a memory 704, processor 706, I/O device(s) 708, a bus 710 and a storage device 712. The choice of processor is not critical as long as the processor 706 has sufficient speed. The memory 704 is any conventional computer memory known in the art. The storage device 712 is a hard drive, CDROM, CDRW, DVD, DVDRW, flash memory card or any other storage device. The computing device is able to include one or more network interfaces 702. An example of a network interface includes a network card connected to an Ethernet or other type of LAN. The I/O device(s) 708 are able to include one or more of the following: keyboard, mouse, monitor, display, printer, modem and other devices. Software used to create the online professional badge is likely to be stored in the storage device 712 and memory 704 and processed as an application is typically processed.

Examples of suitable computing devices include a personal computer, laptop computer, computer workstation, a server, mainframe computer, mini-computer, handheld computer, personal digital assistant, cellular/mobile telephone, smart appliance, gaming console or any other suitable computing device.

The present invention has been described in terms of specific embodiments incorporating details to facilitate the understanding of principles of construction and operation of the invention. Such reference herein to specific embodiments and details thereof is not intended to limit the scope of the claims appended hereto. A person skilled in the art would appreciate that various modifications and revisions to the buyer-provider matching algorithm will occur. Consequently, the claims should be broadly construed, consistent with the spirit and scope of the invention, and should not be limited to their exact, literal meaning.