SYSTEM AND METHOD FOR GENERATING RECOMMENDATIONS FOR RURAL HEALTHCARE

CROSS REFERENCE TO RELATED APPLICATIONS

[1] This application is a Patent of Addition application of Indian Patent Application No. 1317/CHE/2010, entitled "System And Method For Generating Recommendations", filed on May 11, 2010.

BACKGROUND

[2] The invention relates generally to a method and system for generating recommendations and, more particularly, to a method and system for generating recommendations that may be used by organizations that work for the benefit of poor people.

[3] Typically, in developing countries like India, low-income consumers or poor people do not have access to basic products and services. The basic products and services may include affordable and quality healthcare services, financial services, reliable electricity, clean drinking water, and the like. In developing countries, the low-income consumers or poor people, for example, may include agricultural workers, farmers, fishermen, low-skilled laborers, owners of small shops or microenterprises, and so forth, in both urban and rural areas. Many organizations endeavor to provide the basic products and services to these low-income consumers or poor people. These organizations may include non-governmental organizations (NGO), government organizations, healthcare organizations, micro finance organizations, and the like.

[4] Furthermore, the low-income consumers or poor people generally reside in rural areas, and do not have sufficient steady income. Therefore, these organizations face major challenges in collecting and analyzing information and data pertinent to the low-income consumers. For example, since the low-income consumers or the poor people do not have sufficient steady income, it is challenging for a microfinance organization to determine income of poor people or low-income consumers. Similarly, it is challenging for a healthcare organization to determine the affordability and thus the market potential of quality healthcare services for the low-income consumers or poor people.

[5] Moreover, offering the basic products and services to the low- income consumers or poor people becomes more challenging, since each of these organizations works independently of one another, and do not share respective data, knowledge and information with one another. For example, a healthcare organization may not be able to determine a market potential of a respective healthcare product or service based upon a data available with a microfinance organization, such as, liability, asset, income and expenditure of a low-income consumer. Also, the healthcare organization may not be able to determine affordable and quality healthcare services that may be offered to the low-income consumer based upon the data available with the microfinance organization.

[6] Furthermore, demand, supply or market potential of the basic products and services offered by these organizations are interdependent. However, since the organizations work independently of one another, these organizations are unable to take an advantage of the interdependency of the demand, supply and market potential of the basic products and services. For example, a demand for healthcare insurances may increase when small-scale loans are provided to the low-income consumers for setting up new small-scale businesses. The small-scale businesses may increase the purchasing power of the low-income consumers, and thus, the low-income consumers may afford the healthcare insurances. Similarly, the setting up of the new small-scale businesses may increase demand of new electricity connections that are provided by power- providing organizations. Also, an absence of a reliable power source in regions of the small-scale businesses may increase a demand of unconventional sources of lighting or power. However, since these organizations work independently of one another, healthcare organizations and the power-providing organizations may not be aware of the new small-scale businesses. Thus, the healthcare organizations and the power-providing organizations may not offer respective healthcare services and the new electricity connections, respectively to the owners of the new small-scale businesses.

[7] It is therefore desirable to provide a system and a method that allow the organizations to share respective information, knowledge and data with one another. It is further desirable to provide a system and method that identify and evaluate a market potential for offering one or more basic products and services to the low-income consumers based upon information, knowledge and data available with the organizations. Furthermore, there is a need of a system and method that allow the organizations to take an advantage of the interdependency of the demand, supply and market potential of the basic products and services.

BRIEF DESCRIPTION

[8] Briefly, in accordance with one aspect of the technique, a healthcare recommendation system for planning a new healthcare centre is disclosed. The healthcare recommendation subsystem comprises a receiving device configured to receive one or more inputs related to one or more incoming consumers for planning the new healthcare centre, and a healthcare recommendation subsystem configured to receive consumer-specific data from a plurality of organizations based upon the inputs, estimate a market size based upon the consumer-specific data and the inputs, and estimate one or more potential resource requirements based upon the market size.

[9] In accordance with a further aspect of the technique, a healthcare recommendation method for planning a new healthcare centre is disclosed. The healthcare recommendation method comprises the steps of receiving one or more inputs related to one or more incoming consumers for planning the new healthcare centre, receiving consumer-specific data from a plurality of organizations based upon the inputs, estimating a market size based upon the consumer-specific data and the inputs, and estimating one or more potential resource requirements based upon the market size.

DRAWINGS

[10] These and other features, aspects, and advantages of the present invention will become better understood when the following detailed description is read with reference to the accompanying drawings in which like characters represent like parts throughout the drawings, wherein:

[11] FIG. 1 is a block diagram representation of a recommendation system for generating one or more recommendations, in accordance with an exemplary embodiment of the present technique;

[12] FIG. 2 is a flow chart illustrating an exemplary method for generating one or more recommendations, in accordance with aspects of the present technique;

[13] FIG. 3 is a flow chart illustrating an exemplary method for generating a recommendation by analyzing extracted one or more relevant portions of the consumer-specific data of FIG. 2, in accordance with aspects of the present technique;

[14] Fig. 4 is a block diagram of an exemplary recommendation system for generating one or more healthcare recommendations, in accordance with aspects of the present technique;

[15] Fig. 5 is a flowchart of an exemplary method for generating one or more healthcare recommendations for planning a new healthcare centre, in accordance with aspects of the present technique; and

[16] Fig. 6 is a flowchart of an exemplary method for generating one or more healthcare recommendations required for managing an existing healthcare centre, in accordance with aspects of the present technique.

DETAILED DESCRIPTION

[17] As discussed in detail below, embodiments of the invention include a recommendation system that generates one or more recommendations. As used herein, the term "recommendations" may be used to refer to alerts, messages or answers to one or more queries that may be used for the benefit of low-income consumers. By way of a non-limiting example, the recommendations may include a market potential of basic products and services, a risk associated with offering the basic products and services, a number of low- income consumers that may not pay a loan installment in the subsequent month due to illness and loss of working days, a number of loan applications filed by the low-income consumers that may be approved, names of the low-income consumers that may be provided loans, and the like.

[18] The recommendations are generated based upon respective consumer-specific data received from a plurality of organizations that offers the basic products and services to the low-income consumers. More particularly, the recommendations are generated based upon extracted one or more relevant portions of the received consumer-specific data. Further, as used herein, the term "consumer-specific data" may be used to refer to details of the low-income consumers, details of the basic products and services offered to or availed by the low-income consumers, details of a region of residence of the low-income consumers, and the like. As used herein, the term "one or more relevant portions of the received consumer-specific data" may be used to refer to one or more portions of the consumer-specific data that may be relevant or may be used to generate the recommendations. As previously noted, the basic products and services, for example, may include clean drinking water, food, small-scale loans, electricity, and the like. In addition, the plurality of organizations, for example, may include a microfinance organization, a healthcare organization, a power grid organization, a rural marketing organization, a rural water provider, and the like.

[19] It may be noted that since one or more of the respective consumer- specific data corresponds to the poor people or the low-income consumers that do not have sufficient steady source of income and generally reside in rural areas, the basic structure of the respective consumer-specific data may be different from similar data that corresponds to high-income consumers. Thus, one or more portions of the received consumer-specific data may have fuzzy values and have fuzziness. As used herein, the term "fuzzy values" may be used to refer to qualitative values, approximate values, or a combination thereof. For example, since most of the low-income consumers do not have a stable and reliable source of income, the income of the low-income consumers may not be an exact figure, and is generally approximate. Thus, the income of the low-income consumers has a fuzzy value. Similarly since most of the low-income consumers do not have bank accounts, the savings of the low-income consumers may be in the form of agricultural produce and other commodities.

[20] Furthermore, the recommendations, for example, may be used by the organizations to establish a new business, expand existing business and long- term planning. For example, a microfinance organization may use the recommendations to expand to provide healthcare services along with small-scale loans to the low-income consumers. Moreover, the recommendations may be used by the organizations to assess an associated credit risk before providing or offering one or more of the basic products and services. For example, a microfinance organization may evaluate a credit risk associated with offering a small-scale loan to a low-income consumer. The recommendations may also be used by the low-income consumers to know about government programs that are launched by government for the benefit of the low-income consumers. The government programs, for example, may include national rural employment guarantee program (NREGA), Rashtriya Swasthya Bima Yojana (RSBY), and the like.

[21] Referring now to FIG. 1, a block diagram of an exemplary recommendation system 10 for generating one or more recommendations is illustrated. As used herein, the term "recommendations" may be used to refer to alerts, messages or answers to queries that may be used for the benefit of low- income consumers. By way of a non-limiting example, the recommendations may include a market potential of basic products and services, a risk associated with offering the basic products and services to the low-income consumers, a number of the low-income consumers that may not repay a loan installment in the subsequent month due to illness and loss of working days, a number of small- scale loan applications filed by the low-income consumers that may be approved, names of the low-income consumers that may be provided loans or healthcare services, and the like.

[22] Furthermore, the recommendation system 10 includes a plurality of organizations. The plurality of organizations may be used to refer to organizations that work for the benefit of the low-income consumers, organizations that generate data pertinent to the low-income consumers, organizations that offer basic products and services to the low-income consumers, and the like. By way of a non-limiting example, the plurality of organizations may include microfinance organizations, healthcare organizations, nongovernmental organizations, organizations that generate census, government organizations, power grid organizations, water providers in rural areas, rural marketing organizations, and the like.

[23] Moreover, each of the plurality of organizations has a respective consumer-specific data. As previously noted, the term "consumer-specific data" may be used to refer to details of the low-income consumers, details of the basic products and services offered to or availed by the low-income consumers, details of a region of residence of the low-income consumers, and the like. The details of the low-income consumers, for example, may include names, family details, income details, profession details, expenditure details, liabilities, assets, financial details, health details, and the like. Similarly, the details of the basic products and services offered to or availed by the low-income consumers, for example, may include an amount of loan offered to or availed by a low-income consumer, associated risk parameters while offering one or more of the basic products and services, and the like. Further, the details of the region of residence of the low- income consumers, for example, may include quality of healthcare in a region, census data, demographic data, social data, economic data of one or more regions, and the like. The plurality of organizations may store the respective consumer-specific data in a data repository, a notebook, a file, and the like.

[24] As previously noted, one or more portions of the respective consumer-specific data may have fuzzy values. More particularly, one or more portions of the details of the low-income consumers, the details of the basic products and services offered to or availed by the low-income consumers and the details of a region of residence of the low-income consumers may have fuzzy values. As used herein, the term "fuzzy values" may be used to refer to values that are qualitative values, approximate values, or a combination thereof. The qualitative values are values of the portions of the consumer specific data that define quality of the basic products and services. By way of an example, healthcare services in a region may be categorized based upon quality of services offered to the low-income consumers, and the category of the healthcare services may be bad, good, excellent, and the like. Accordingly, bad, good or excellent values are qualitative values or fuzzy values.

[25] Furthermore, the approximate values may be used to refer to the values that are approximation of a range of values. The fuzzy values that may be approximate values may include income, surplus income, expenditure, savings of the low-income consumers, and the like. For example, since the low-income consumers do not have steady source of income or steady income, the income of the low-income consumers is an approximate value and thus, is a fuzzy value. By way of another example, since most of the low-income consumers do not have bank accounts, the savings of the low-income consumers may be in the form of agricultural produce and other commodities and thus, the savings has fuzzy values.

[26] As shown in a presently contemplated configuration, the plurality of organizations includes a micro finance organization 12, an organization 14 that generates census, a healthcare organization 16 and a government organization 18. The micro finance organization 12 has a first consumer-specific data 20 that generally includes information that is required for offering small-scale loans to the low-income consumers. By way of a non-limiting example, the first consumer-specific data 20 may include names, income, savings, family details, purchasing power, expenditure, assets, liability of the low-income consumers, an amount of loan availed, a number of pending loan installments, details of loan repayment, and the like. Further, the organization 14 that generates census has a second consumer-specific data 22. The second consumer-specific data 22 of the organization 14 may include census data, demographic data, social data, economic data of one or more regions, and the like. Similarly, the healthcare organization 16 has a third consumer-specific data 24 that may include names, health history, current illness, health services availed by the low-income consumers, and the like. Furthermore, the government organization 18 has a fourth consumer-specific data 26. By way of a non-limiting example, the fourth consumer-specific data 26 may include details of funds available for healthcare of the low-income consumers, details of funds available for providing electricity to the low-income consumers, names of organizations working for the benefit of the low-income consumers, details of one or more programs initiated by government for the benefit of low-income consumers, and the like.

[27] In accordance with aspects of the present technique, the recommendation system 10 further includes a receiving device 28 that receives the respective consumer-specific data 20, 22, 24, 26 from the organizations 12, 14, 16, 18. The receiving device 28, for example, may include a receiver, a card reader, a keyboard, a scanner, or combinations thereof. In one embodiment, the consumer-specific data 20, 22, 24, 26 may be entered manually via the receiving device 28, such as, a keyboard. In another embodiment, the consumer-specific data 20, 22, 24, 26 may be sent to the receiving device 28, via e-mails, data transfer techniques, and the like. In certain embodiments, the receiving device 28 may include a first module 30 that sends requests for an updated consumer- specific data to the organizations 12, 14, 16 18 at a predetermined interval of time. The organizations 12, 14, 16, 18 may send the updated consumer-specific data to the receiving device 28 in response to the requests for the updated consumer-specific data.

[28] Furthermore, in one embodiment, the receiving device 28 sends
the received consumer-specific data 20, 22, 24, 26 to a data repository 32 and/or a recommendation subsystem 34. In one embodiment, the recommendation subsystem 34 may receive the consumer-specific data 20, 22, 24, 26 from the receiving device 28. In another embodiment, the recommendation subsystem 34 may receive the consumer-specific data 20, 22, 24, 26 from the data repository 32. The recommendation subsystem 34 extracts one or more portions 33 of the received consumer-specific data 20, 22, 24, 26. The portions 33 may have fuzzy values or fuzziness. In the presently contemplated configuration, the portions 33 of the received consumer-specific data 20 may include income, savings, expenditure and purchasing power. Furthermore, the recommendation subsystem 34 adaptively adjusts the portions 33 of the received consumer-specific data 20, 22, 24, 26. The recommendation subsystem 34 adaptively adjusts the portions 33 by using techniques including a fuzzy arithmetic technique, an arithmetic of ranges technique, fuzzy logic, and the like. For example, the recommendation subsystem 34 may adjust the income by splitting the income in to a range by using the arithmetic of ranges technique. In certain embodiments, the recommendation subsystem 34 may adaptively adjust the portions 33 based upon domain knowledge. For example, if savings of a farmer are in the form of agricultural produce and other commodities, then the recommendation subsystem 34 may equate the savings to the market value of the agricultural produce and the other commodities. It may be noted that the adaptive adjustment of the portions
33 minimizes fuzziness in the portions 33. Accordingly, the portions 33 are more reliable for generation of recommendations.

[29] The adaptive adjustment of the portions 33 generates adaptively adjusted portions 35 that are sent to the data repository 32. The data repository 32 stores the adaptively adjusted portions 35. Moreover, the recommendation subsystem 34 extracts one or more relevant portions 37 of the consumer-specific data 20, 22, 24, 26 and/or the adaptively adjusted portions 35. In addition, the recommendation subsystem 34 generates the recommendations based upon the relevant portions 37. The generation of the recommendations based upon the relevant portions 37 will be explained in greater detail with reference to FIGs. 2 and 3.

[30] In one embodiment, the recommendations may be displayed on a display device 36. In another embodiment, the recommendations may be printed on a printer via a printer 38. In certain other embodiments, the recommendations may be transmitted to one or more of the organizations via e-mails, data transfer techniques, and the like. Also, in certain embodiments, the recommendations may be transmitted to a handheld device (not shown), a mobile device (not shown), and the like. As shown in the presently contemplated configuration, a recommendation 11 is sent by the recommendation subsystem 34 to the micro finance organization 12.

[31] The generated recommendations may be used by the plurality of organizations 12, 14, 16, 18 for a long term planning, risk assessment, an expansion of a range of the basic product and services, and the like. For example, if the micro finance organization 12 plans to expand to provide healthcare services along with small-scale loans in a region, then the recommendation system 10 may generate recommendations for the micro finance organization 12, such as, a market size for healthcare products in the region, a demand of the healthcare products in the region, a number of patients in the region, a price range of the healthcare products available in the region, and the like.

[32] Referring now to FIG. 2, a flow chart 100 illustrating an exemplary method for generating one or more recommendations, is depicted. The recommendations, for example may be generated by the recommendation subsystem 34. The method starts at step 102 where respective consumer-specific data is received from a plurality of organizations that offers basic products and services to low-income consumers or poor people. The respective consumer- specific data may be received by the receiving device 28 (see FIG. 1). In one embodiment, the consumer-specific data may be entered manually via the receiving device 28. In another embodiment, the consumer-specific data may be received via digital techniques, such as, e-mails or other data transfer techniques. The received consumer-specific data may include the first consumer-specific data 20, the second consumer-specific data 22, the third consumer-specific data 24 and the fourth consumer-specific data 26.

[33] Furthermore, at step 104, one or more adaptively adjusted portions may be generated. As previously noted with reference to FIG. 1, the one or more adaptively adjusted portions may be generated by adaptively adjusting one or more portions of the received consumer-specific data that has fuzzy values. The portions of the received consumer-specific data that has fuzzy values may be adaptively adjusted by using techniques including a fuzzy arithmetic technique, an arithmetic of ranges technique, fuzzy logic, and the like.

[34] Moreover, at step 106, one or more queries may be received from one or more of the plurality of organizations. The queries may be received by the receiving device 28. The queries are sent by one or more of the organizations to receive the recommendations in response to the queries. For example, if a microfinance organization plans to expand in ten regions, then other organizations, such as, a healthcare organization may plan to expand in the ten regions. Accordingly, the healthcare organization may send queries to the receiving device 28 to receive recommendations related to a number of regions where the microfinance organization plans to expand, details of the expansion plans, demographic, social and economic details of the ten regions, and the like. In one embodiment, the queries sent by the organizations may accompany a request to receive recommendations at a predetermined interval of time. For example, a microfinance organization may send a query to receive the recommendations related to names of potential loan installment defaulters, and the query may be accompanied with a request to receive the recommendations every month.

[35] Furthermore, at step 108, one or more relevant portions of the received consumer-specific data and/or the adaptively adjusted portions may be extracted. The one or more relevant portions of the consumer-specific data may be extracted by the recommendation subsystem 34 (see FIG. 1). In one embodiment, the one or more relevant portions of the consumer-specific data may be extracted based upon the one or more queries. For example, the extracted one or more relevant portions of the consumer-specific data may include name of a low-income consumer, expenditure of the low-income consumer, a number of family members, liabilities and assets of the family members when a query is sent by a microfinance organization to receive the recommendations related to a risk associated with offering a loan to the low-income consumer. By way of another example, the extracted one or more relevant portions of the consumer-specific data may relate to a number of organizations, names of the organizations and other details of the organizations working in a region when a query is sent by a healthcare organization to receive the recommendations related to an existing infrastructure in a region where the healthcare organization plans to offer its healthcare services.

[36] Moreover, at step 110, the recommendations may be generated based upon the extracted one or more relevant portions of the consumer-specific data. In one embodiment, the recommendations may be the extracted one or more relevant portions of the consumer-specific data. For example, if a query is sent to receive a recommendation related to a mortality rate in a region and the extracted one or more relevant portions of the consumer-specific data included the mortality rate, then the recommendation may include the mortality rate in the region.

[37] In another embodiment, the recommendations may be generated based upon an analysis of the extracted one or more relevant portions of the consumer-specific data. The analysis of the extracted one or more relevant portions of the consumer-specific data may be carried out based upon the queries. An exemplary analysis of exemplary extracted one or more relevant portions of the consumer-specific data based upon a query received from a healthcare organization is illustrated in FIG. 3.

[38] Referring now to FIG. 3, a flow chart 300 illustrating an exemplary method for analyzing the extracted one or more relevant portions of the consumer-specific data of FIG. 2, is depicted. More particularly, an exemplary embodiment of step 110 of FIG. 2 is explained in greater detail. Reference numeral 302 is representative of a query that is sent by a healthcare organization. The query 302 is received at step 106 of FIG. 2. In the exemplary technique, the query 302 requests for recommendations related to a healthcare service that may be offered to a low-income consumer. Furthermore, reference numeral 304 is representative of the extracted one or more relevant portions of the consumer-specific data that are extracted by the recommendation subsystem 34. The one or more relevant portions 304 of the consumer-specific data are extracted at step 108 of FIG. 2. As previously noted with reference to FIG. 2, the one or more relevant portions 304 of the consumer-specific data are extracted by the recommendation subsystem 34 based upon the query 302. In this example, the extracted one or more relevant portions 304 of the consumer-specific data include a number of family members of the low-income consumer, income of all the working family members, expenses of the family members, liability, assets profession, and health of the family members.

[39] In the exemplary embodiment, a surplus income and healthcare demand of the family members is determined at step 306. The surplus income, for example, may be determined by subtracting a total expenditure of the family members from a total income of the family members. In one embodiment, the total income of the family members is determined by adding income of all the working family members. Similarly, the total expenditure of the family members is determined by adding expenses and liability of all the family members. In addition, the healthcare demand may be determined based upon the health of the family members. It may be noted that since the income and expenditure of the low-income consumers may have fuzzy values or fuzziness, the determination of the total income, the surplus income, the total expenditure, and the like may be determined by using techniques, such as, a fuzzy arithmetic technique, fuzzy logic, arithmetic of ranges, and the like.

[40] Furthermore, at step 308, the recommendations may be generated based upon the surplus income and the health of the family members. For example, if one of the family members has a health problem, then the recommendations may include an affordable healthcare product or an affordable healthcare service for the family member having the health problem. Further, the recommendations may include an affordable health insurance for the family members.

[41] Referring now to Fig. 4, a block diagram of an exemplary recommendation system 10' for generating one or more healthcare recommendations is illustrated. The recommendation system 10' is an exemplary embodiment of the recommendation system 10 of FIG. 1. As used herein, the term "healthcare recommendations" may be used to refer to recommendations required for planning a new healthcare centre in a specified region and recommendations required for managing an existing healthcare centre. As shown in FIG. 4, the healthcare recommendation system 10' includes a healthcare recommendation subsystem 400 that generates the healthcare recommendations.
The healthcare recommendation subsystem 400 is an exemplary embodiment of the recommendation subsystem 34 of FIG. 1.

[42] As shown in the presently contemplated configuration, the healthcare recommendation subsystem 400 is operationally coupled to a plurality of organizations 402. As previously noted with reference to FIG. 1, the organizations 402 may include microfinance organizations, healthcare organizations, non-governmental organizations, organizations that generate census, government organizations, power grid organizations, water providers in rural areas, rural marketing organizations, and the like. In one embodiment, the organizations 402 may be the microfinance organization 12, organization 14 that generates census, healthcare organization 16 and government organization 18 (see FIG. 1).

[43] As previously noted with reference to FIG. 1, the healthcare recommendation subsystem 400 is operationally coupled to the display device 36 and printer 38. In addition, the healthcare recommendation subsystem 400 is operationally coupled to an receiving device 404 to receive one or more inputs 406 from a user. The inputs 406, for example, may include the location of a region where a new healthcare centre will exist, healthcare services that will be offered in the new healthcare centre, size of the new healthcare centre, or the like. For example, when a user plans to open a new healthcare centre in a village named "Nallurhalli" in Karnataka that has general medicine facilities, then the inputs 406 may include 'Nallurhalli', 'Karnataka' and 'general medicine'.

[44] Subsequent to the receipt of the inputs 406, the healthcare recommendation subsystem 400 may extract consumer-specific data 408 based upon the inputs 406. The consumer-specific data 408, for example, may include population, birth rate, mortality rate, average income of consumers, or the like. Subsequent to the receipt of the consumer-specific data 408, the recommendation subsystem 400 may generate the healthcare recommendations by processing the consumer-specific data 408. The generation of the healthcare recommendations will be explained in greater detail with reference to FIGs. 5 and 6.

[45] Moreover, the exemplary healthcare recommendation subsystem 400 includes a planning module 410 and a management module 412. The planning module 410 generates healthcare recommendations for planning a new healthcare centre in a determined region or as specified in the inputs 406. The healthcare recommendations generated by the planning module 410, for example, may include a market size in a predefined region, demand of predefined healthcare services in the determined region, resource requirements in the determined region, infrastructure planning, human resource requirements, optimized layout plan, regulatory requirements, operational planning, and the like. The management module 412 generates healthcare recommendations for managing an existing healthcare centre. For example, the management module 412 generates healthcare recommendations, such as, expected operating expenses of the existing healthcare centre, expected operating margin of the existing healthcare centre, expected revenues that may be earned from the healthcare centre, an optimized schedule for an incoming consumer, and the like. The generation of the healthcare recommendations by the planning module 410 and management module 412 will be explained in greater detail with reference to FIGs 5 and 6. As shown in FIG. 4, the healthcare recommendation subsystem 400 may be operationally connected to the data repository 32 (also see FIG. I). The healthcare recommendation subsystem 400 may store and retrieve intermediate data, the inputs 406, consumer-specific data 408, and the like in the data repository 32. The data repository 32 may also include one or more regulatory requirements that are to be complied with for establishing a new healthcare centre in a region.

[46] Turning now to Fig. 5, a flowchart 500 of an exemplary method for generating one or more healthcare recommendations for planning a new healthcare centre is illustrated. The healthcare recommendations for planning the new healthcare centre, for example, may be generated by the planning module 410 (see FIG. 4). As previously noted with reference to FIG. 4, the healthcare recommendations generated by the planning module 410 may include market size in a determined region, demand of determined healthcare services in the determined region, resource requirements in the determined region, infrastructure planning, human resource requirements for the establishing a new healthcare centre in the determined region, optimized layout plan, regulatory requirements, operational planning, required investment, and the like. At step 502, one or more inputs 406 (also see FIG. 4) may be entered by a user. As previously noted with reference to FIG. 4, the inputs 406, for example, may include the name of a region where a new healthcare centre will exist, healthcare services that will be offered in the new healthcare centre, size of the healthcare centre, an area of land where the new healthcare centre will be established, or the like.

[47] At step 504, consumer-specific data may be received based upon the inputs 406. For example, when a user plans to open a new healthcare centre A in a region, then the inputs 406 entered by the user may include the name of the region, healthcare services that the new healthcare centre A will offer and size of the new healthcare centre A. In this example, consumer-specific data extracted based upon the inputs 406 may include population of the region, the number of existing healthcare centers in the region, birth rate, mortality rate, disease concentration in the region, approval required, and the like. The consumer- specific data may be received from the organizations 12, 14, 16, 18, 402 (see FIG. 1 and FIG. 4). Furthermore, as previously noted, at step 506 the planning module 410 (see FIG. 4) may adaptively adjust one or more portions of the consumer-specific data to generate adaptively adjusted consumer-specific data.

[48] Subsequently at step 508, a market size of the healthcare services (specified in the inputs 406) that will be offered by the new healthcare centre may be estimated. The market size, for example, may be estimated based upon the inputs 406, the consumer-specific data and the adaptively adjusted consumer- specific data. By way of a non-limiting example, the market size may be estimated by using one or more prediction techniques, such as, a competitor analysis technique, a time series analysis technique, an analysis of socio economic data, or combinations thereof In one embodiment, when the healthcare centre B is a hospital, then the market size may include an expected number of patients in a year and purchasing capacity of the expected number of patients. Furthermore, at step 510, a check may be carried out to determine whether establishing the new healthcare centre is viable. The check is carried out based upon the market size that has been determined at step 508. For instance, if the market size shows that the expected number of consumers in the new healthcare centre is below a predetermined number, then establishing the new healthcare centre is not viable.

[49] At step 510, if it is determined that opening the new healthcare centre is not viable, then the control is transferred to step 502. At step 502, new inputs may be entered by the user. Alternatively, at step 510, if it is determined that establishing the new healthcare centre is viable, then the control may be transferred to step 512. At step 512, one or more potential resource requirements may be determined. Consequent to the determination of the potential resource requirements, potential resources that will be required for establishing the new healthcare centre may be determined. By way of a non-limiting example, the potential resources may include requirements of furniture, equipments, machines, human resources, and the like. In one embodiment, when the new healthcare centre is a hospital, then the human resources may include doctors, nurses, technicians, administration staff, and the like. The potential resource requirements, for example, may be determined using one or more techniques including mathematical programming techniques, heuristic methods, and the like. In one embodiment, the potential resource requirements are determined based upon the market size.

[50] Furthermore, at step 514, one or more regulatory requirements may be extracted from the data repository 32 based upon the potential resource requirements, inputs 406 and the consumer-specific data. For instance, if the new healthcare centre plans to offer maternity services, then the regulatory requirements includes various mandatory requirements imposed by the government for offering the maternity services in a healthcare centre. Subsequently, at step 518, a layout plan for the new healthcare centre may be generated. The layout plan, for example, may be determined based upon the regulatory requirements, potential resource requirements, or combinations thereof. In one embodiment, when an available land area is received in the inputs 406, the layout plan may be determined based upon the regulatory requirements, potential resource requirements, and the available land area. More particularly, the layout plan is determined such that the available land area is optimally used, the regulatory requirements are met and movement of each consumer in the new healthcare centre is minimized.

[51] Furthermore, at step 518, one or more parameters may be determined. As used herein, the term "parameters" may be used to refer to one or more factors that may be used to determine whether the potential resources and the layout plan are optimal. The parameters, for example, may include percentage utilization of the potential resources and the layout plan, average waiting time of each consumer, an average time spent for availing a healthcare service by a consumer, and the like. The parameters may be determined using discrete event simulation techniques.

[52] Furthermore, at step 519, a consumers' inflow 520 for each of the healthcare services that will be offered in the new healthcare centre is estimated. As used herein, the term "consumers' inflow" may be used to refer to an optimized sequence of events that may be followed by a consumer for availing each healthcare service, wherein each optimized sequence of events is mapped to a healthcare service.

[53] Subsequently, at step 522, a check may be carried out to determine whether the potential resources and the layout plan are optimal. In one embodiment, whether the potential resources and the layout plan are optimal may be determined based upon one or more of the parameters. For instance, if an average waiting time of each consumer is more than a predefined time, then the potential resources are not optimal. Similarity, if few wards in the new healthcare centre are often empty, then the number of wards in the layout plan may be reduced. At step 522, if it is determined that the number of resources are not optimal, then the control is transferred to step 512. At step 512, new potential resource requirements may be determined. However, at step 522 if it is determined that potential resources and the layout plan are optimal, then optimized potential resources 524 and optimized layout plan 526 are determined. More particularly, the latest determined potential resources and the layout plan are declared as the optimized potential resources 524 and optimized layout plan 526.

[54] Furthermore, at step 528, expected capital investments required for establishing the new healthcare centre may be determined. The expected capital investments, for example may be determined based upon the optimized resources 522 and the optimized layout plan 526. By way of a non-limiting example, if the optimized potential resources 524 include five doctors, five equipments, ten nurses, two administration staff, and the optimized layout plan 526 requires five acres of land, then an expected capital investment may be determined utilizing unit cost price of each of the optimized potential resources 524 and cost price of the four acres of land.

[55] In one embodiment, at step 530, a selling price of each of the healthcare services that will be offered in the new healthcare centre is fixed. The selling price, for example, may be fixed by a user. In certain embodiments, the selling price of each of the healthcare services may be entered by the user via the receiving device 404. Subsequently, expected revenues of the new healthcare centre may be estimated at step 532. The expected revenues, for example, may be estimated based upon the market size and the selling price of each of the healthcare services. Subsequently at step 534, an expected operating margin of the new healthcare centre may be determined. In one embodiment, the expected operating margin may be determined based upon the expected revenues and the expected investments.

[56] Turning now to Fig. 6, a flowchart 600 of an exemplary method for generating one or more healthcare recommendations required for managing an existing healthcare centre, is depicted. The healthcare recommendations for managing the existing healthcare centre are generated by the management module 412 (see FIG. 4). Reference numeral 602 is representative of incoming consumers who desire to avail one or more healthcare services in the existing healthcare centre. In one embodiment, the incoming consumers 602 may be low- income consumers and uneducated. At step 604, consumer-specific data related to the incoming consumers 602 may be received. The consumer-specific data, for example, may be received from the incoming consumers 602, or relatives or friends of the incoming consumers 602. The consumer-specific data, for example, may include the name of an incoming consumer, occupation of the incoming consumer, annual income, health history, name of previous healthcare centre where one or more healthcare services were availed in past, name of healthcare service that the incoming consumer wishes to avail, and the like.

[57] In certain embodiments, one or more of the incoming consumers 602 are low-income consumers and uneducated. Thus, such low-income or uneducated incoming consumers may not be able to provide each required detail to complete the consumer-specific data. Accordingly, in such embodiments, the consumer-specific data received may be a partial consumer-specific data. For example, an uneducated incoming consumer may not be able to provide details about health history that may be required by a doctor. Therefore, at step 606, additional consumer-specific data related to the one or more of the incoming consumers 602 may be received from the organizations 12, 14, 16, 18, 402 (see FIG. 1 and FIG. 4). In one embodiment, the additional consumer-specific data may include the details that the uneducated or low-income consumer was unable to provide. In such embodiments, the additional consumer-specific data may be received based upon the partial consumer-specific data. Consequent to the receipt of the additional consumer-specific data, final consumer-specific data 608 is generated. More particularly, the final consumer-specific data includes the partial consumer-specific data and the additional consumer-specific data.

[58] Reference numeral 610 is representative of available resources required for providing one or more healthcare services. The available resources, for example, may include operation theatre, doctors, computed tomography scanner, specialized doctors and the like. Additionally, the schedule of available resources may include available resources mapped to the time of availability. For example, a skin specialist doctor may be available from 9 am to 12 pm. Similarly, operation theatre may be available from 10 am to 12 pm. Furthermore, as previously noted with reference to FIG. 5, reference numeral 520 is representative of consumers' inflow. As previously noted with reference to FIG. 5, the term "consumers' inflow" is used herein to refer to an optimized sequence of events that may be followed by an incoming consumer for availing each healthcare service, wherein each optimized sequence of events is mapped to a healthcare service.

[59] At step 612, an optimized schedule is generated for each of the incoming consumers 602 based upon the consumers' inflow 520, the schedule of availability of resources 610 and the final consumer-specific data 608. As used herein, the term "optimized schedule" is used to refer to an optimized sequence of events that an incoming consumer needs to follow for availing a healthcare service. In one embodiment, the optimized schedule is consistent with the consumers' inflow. Alternatively, the optimized schedule is generated such that available resources are optimally used, a number of incoming consumers who avail healthcare services is maximized, an overall cost of providing healthcare services is minimized, or combinations thereof. An exemplary optimized schedule of an incoming consumer B who wishes to avail a healthcare service. In an embodiment, when the healthcare service is health check up, then an exemplary optimized schedule may be as shown in Table 1.
Table 1

[60] As shown in the exemplary Table 1, an optimized schedule may
include a name of each event, a location for execution of each event, a date and time for execution of each event. Subsequently, at step 614, each of the incoming consumers 602 may be offered one or more healthcare services based upon the optimized schedule. At step 616, an average waiting time for availing each healthcare service by each of the incoming consumers 602 may be determined. An average waiting time of an incoming consumer, for example may be determined by determining an average of waiting times of the incoming consumer for initiating an execution of each event in the optimized schedule. For example, with reference to Table 1, if a waiting time for initiation of the events general check up, eyes check up, X-Ray, and blood check up are w1, w2, w3 and w4, respectively, then an average waiting time for the incoming consumer is an average of the waiting times W|, w2, w3, W4. Additionally, at step 618, an average time required for completion of each event is determined. For instance, in the example of Table 1, an average time for completion of the events including check up, eyes check up, X-Ray, and blood check up are determined.

[61] In certain embodiments, at step 620, one or more bottlenecks in the operation of the existing healthcare centre may be determined. The bottlenecks, for example may be determined based upon the average waiting time of each of the incoming consumers 602 and the average time required for completion of each event. For instance, if an average waiting time of the incoming consumers 602 is high at a reception, then the bottleneck may be reception of the healthcare centre. The bottlenecks may be used to improve the efficiency of the existing healthcare centre.

[62] The various embodiments of the invention allow organizations that work for the benefit of poor people or low-income consumers to share respective data, knowledge and information with one another. Furthermore, the present techniques allow the organizations to start a new business or expand existing business by using data received from other organizations. For example; if an organization, such as, a microfinance organization plans to provide healthcare services to rural population in a particular region, then the present techniques may provide the microfinance organization with recommendations including a number of patients in the region, a price range of healthcare products in the region, and the like. Furthermore, the invention facilitates the organizations to determine a market potential of basic products and services in one or more regions. Also, the present system and method enables the organizations to receive recommendations related to a risk associated with offering the basic products and services to the low-income consumers or poor people. The present techniques may also allow the low-income consumers and the poor people to get recommendations, such as, programs initiated by the government for the benefit of the low-income consumers or poor people, prices of crops, and the like. In certain embodiments, the present invention generated recommendations for to planning a new healthcare centre in a rural area.
Alternatively, the present invention also generates recommendations for managing an existing healthcare centre.

[63] It is to be understood that not necessarily all such objects or advantages described above may be achieved in accordance with any particular embodiment. Thus, for example, those skilled in the art will recognize that the systems and techniques described herein may be embodied or carried out in a manner that achieves or optimizes one advantage or group of advantages as taught herein without necessarily achieving other objects or advantages as may be taught or suggested herein.

[64] While the invention has been described in detail in connection with only a limited number of embodiments, it should be readily understood that the invention is not limited to such disclosed embodiments. Rather, the invention can be modified to incorporate any number of variations, alterations, substitutions or equivalent arrangements not heretofore described, but which are commensurate with the spirit and scope of the invention. Additionally, while various embodiments of the invention have been described, it is to be understood that aspects of the invention may include only some of the described embodiments. Accordingly, the invention is not to be seen as limited by the foregoing description, but is only limited by the scope of the appended claims.

We claim:

1. A healthcare recommendation system for planning a new healthcare centre, comprising:
a receiving device configured to receive one or more inputs related to one or more incoming consumers for planning the new healthcare centre; and
a healthcare recommendation subsystem configured to:
receive consumer-specific data from a plurality of organizations based upon the inputs;
estimate a market size based upon the consumer-specific data and the inputs; and
estimate one or more potential resource requirements based upon the market size.

2. The system as claimed in claim 1, wherein the inputs comprise name of a region where the new healthcare centre will be established, one or more healthcare services that will be offered in the new healthcare centre, a size of the healthcare centre, an area of a land where the new healthcare centre will be established, or combinations thereof.

3. The system of claim 1, wherein the healthcare recommendation subsystem estimates the market size using one or more prediction techniques, such as a competitor analysis technique, a time series analysis technique, an analysis of socio economic data, or combinations thereof

4. The system of claim 1, wherein the market size comprises an expected number of consumers in a year, a purchasing capacity of the expected number of consumers, or combinations thereof.

5. The system of claim 1, wherein the healthcare recommendation subsystem determines the one or more potential resource requirements by utilizing mathematical programming techniques, heuristic methods, or combinations thereof.

6. The system of claim 1, wherein the one or more potential resource requirements comprise furniture, equipments, human resources, machines, or combinations thereof.

7. The system of claim 1, wherein the receiving device comprises a receiver, a card reader, a keyboard, a scanner, a handheld device, or combinations thereof.

8. The system of claim 1, wherein the healthcare recommendation subsystem is further configured to:
extract one or more regulatory requirements based upon the one or more potential resource requirements;
generate a layout plan based upon the one or more regulatory requirements, the one or more potential resource requirements, an available area of land, or combinations thereof.
determine one or more parameters utilizing one or more discrete event simulation techniques; and
estimate optimal resource requirements based on consumers' inflow for each healthcare service that the healthcare centre desires to offer utilizing discrete event system simulation techniques.

9. The system of claim 1, wherein the healthcare recommendation subsystem is further configured to adaptively adjust one or more portions of the consumer-specific data that has fuzzy values to generate adaptively adjusted consumer-specific data.

10. The system of claim 9, wherein the healthcare recommendation subsystem is further configured to determine an expected capital investment, expected revenues and an expected operating margin of the new healthcare centre.

11. The system of claim 1, further comprising a data repository for storing the received consumer-specific data, the inputs, transition data, the potential resource requirements, the market size, or combinations thereof.

12. A healthcare recommendation method for planning a new healthcare centre, comprising:
receiving one or more inputs related to one or more incoming consumers for planning the new healthcare centre;
receiving consumer-specific data from a plurality of organizations based upon the inputs;
estimating a market size based upon the consumer-specific data and the inputs; and
estimating one or more potential resource requirements based upon the market size.