Commission calculation method and device for property community group purchase, equipment and medium

Abstract

The invention provides a commission calculation method and device for property community group purchase, equipment and a medium, and the method comprises the steps: collecting first sales data and first evaluation information after a first account forwards a first group purchase link constructed based on a first commodity; determining first commission information based on the first sales data and a first coefficient of the first commodity; and adjusting the first coefficient to a second coefficient based on the first sentiment classification information and the first keyword determined by the first evaluation information, and determining second commission information determined based on the second coefficient as first target commission information. According to the technical scheme of the embodiment of the invention, the weight coefficient of each factor can be corrected by using the evaluation information of the order, the first commission information is adjusted into the second commission information on the basis of the first commission information, and the application of the second commission information is triggered according to the positive correlation between the adjustment direction of the commission information and the sentiment classification of the comment information. The dynamic adjustment of the weight coefficients of different factors is realized, and the user experience is improved.

Description

Technical Field

[0001] The present invention relates to the field of data processing technology, and in particular to a method, device, equipment, and medium for calculating commissions for property community group purchases. Background Art

[0002] At present, community group buying is a common business in the property sector. Property companies provide specific product group buying according to the needs of community residents, which can effectively improve the experience of residents in the community. Community group buying is usually carried out in the property management APP. After the property management personnel publish the relevant group buying link in the property management APP, both the management personnel and users can purchase through the property management APP, and they can also forward the group buying link. Property companies usually count the sales converted by sharing, calculate the commission according to a certain coefficient and distribute it to the corresponding forwarding account to improve the promotion effect of community group buying.

[0003] In related technologies, the calculation of commissions usually introduces relevant factors, such as the number of orders, consumer satisfaction, product promotion difficulty, etc., and the target commission is calculated based on the sales volume combined with the weight coefficients of each factor. However, in related technologies, the weight coefficient of each factor is usually a preset fixed value, and the products sold by community group purchases are diverse, and the consumption habits of users cannot be predicted in advance. It is difficult for managers to set reasonable weight coefficients, which can easily lead to unreasonable calculated commissions and affect user experience. Summary of the invention

[0004] The present invention aims to solve at least one of the technical problems existing in the prior art. To this end, the present invention proposes a commission calculation method, device, equipment, and medium for property community group buying, which can dynamically adjust the weight coefficient of the calculation factor to improve the user experience.

[0005] In a first aspect, an embodiment of the present invention provides a method for calculating commissions for property community group purchases, which is applied to a property management system, wherein the property management system has multiple preset accounts registered therein, and the method includes:

[0006] Building a first group purchase event based on a first commodity, building a first group purchase link in response to a forwarding request for the first group purchase event from any first account, and associating the first group purchase link with the first account, wherein the first commodity is pre-associated with a plurality of first factors, and each of the first factors is pre-set with a corresponding first weight coefficient;

[0007] determining at least one first order generated based on the first group purchase link, obtaining first evaluation information of each of the first orders, summarizing first sales data of the first orders, and determining first commission information based on the first sales data and the first weight coefficient;

[0008] Determine first sentiment classification information corresponding to each of the first evaluation information based on a preset NLP model, configure the first factor as a mining category of a preset text mining model, and determine first keywords corresponding to each of the first evaluation information based on the configured text mining model, wherein each of the first keywords is associated with one of the first factors;

[0009] Based on any of the first evaluation information, select a target keyword from the first keywords, and determine a first adjustment score of the first factor associated with the target keyword based on the first sentiment classification information and the target keyword;

[0010] Based on any of the first factors, determine a second weight coefficient based on all of the first adjustment scores and the corresponding first weight coefficients, and determine second commission information of the first account based on the first sales data and the second weight coefficient;

[0011] When the change trend from the first commission information to the second commission information is positively correlated with the first emotion classification information, the second commission information is determined as the first target commission information.

[0012] According to some embodiments of the present invention, the property management system is preset with a plurality of preset items, each of the preset items includes a plurality of preset commodities, each of the preset items is configured with a plurality of preset factors, each of the preset factors is configured with a corresponding preset weight coefficient, and after constructing a first group purchase event based on the first commodity, the method further includes:

[0013] Building a second group purchase event based on a second commodity of the first item, wherein the first item is the preset item to which the first commodity belongs;

[0014] In response to a forwarding request for the second group purchase event from any second account, a second group purchase link is constructed, and the second group purchase link is associated with the second account;

[0015] determining at least one second order generated based on the second group purchase link, obtaining second evaluation information of each second order, summarizing second sales data of the second order, and determining third commission information based on the second sales data and the first weight coefficient;

[0016] Determine the second adjustment score of each of the first factors based on the NLP model, the text mining model and the second evaluation information, determine the third weight coefficient based on all of the second adjustment scores and the first weight coefficient, and determine the second target commission information of the second account based on the third weight coefficient.

[0017] According to some embodiments of the present invention, after determining the second target commission information of the second account based on the third weight coefficient, the method further includes:

[0018] determining a fourth weight coefficient based on the third weight coefficient and the second weight coefficient;

[0019] The fourth weight coefficient is associated with the first account.

[0020] According to some embodiments of the present invention, a relevant connection number is set between every two preset related items. After the first group purchase event is constructed based on the first commodity, the method further includes:

[0021] Construct a third group purchase event based on the third product of the second project;

[0022] Based on the correlation coefficient between the first item and the second item, the preset weight coefficient of the second factor corresponding to the third product is updated.

[0023] According to some embodiments of the present invention, after determining the second commission information as the first target commission information, the method further includes:

[0024] Determine the preset account that is determined as the first account and not determined as the second account as a third account, and determine the preset account that is determined as both the first account and the second account as a fourth account;

[0025] Building a fourth group purchase event based on any of the preset commodities in the first project, and building a fourth group purchase link based on the fourth group purchase event;

[0026] When the third account forwards the fourth group purchase link, determining third target commission information of the third account based on the first weight coefficient;

[0027] When the fourth account forwards the fourth group purchase link, fourth target commission information of the fourth account is determined based on the fourth weight coefficient.

[0028] According to some embodiments of the present invention, determining a first adjustment score of the first factor associated with the target keyword based on the first sentiment classification information and the target keyword includes:

[0029] Determine second sentiment classification information of each of the target keywords based on the NLP model;

[0030] When the first emotion classification information is the same as the second emotion classification information, determining a preset first score as the first adjustment score;

[0031] When the first emotion classification information is different from the second emotion classification information, a preset second score is determined as the first adjustment score, wherein the second score is smaller than the first score.

[0032] According to some embodiments of the present invention, there are multiple first accounts, and before determining the second commission information as the first target commission information, the method further includes:

[0033] Determine an increasing account and a decreasing account from the plurality of first accounts, and determine an account quantity ratio of the increasing account and the decreasing account, wherein the second weight coefficient of the increasing account is greater than the first weight coefficient, and the second weight coefficient of the decreasing account is less than the first weight coefficient;

[0034] When the account number ratio is greater than one, reducing the second weight coefficient of the decreasing account based on the account number ratio;

[0035] Alternatively, when the account number ratio is less than one, the second weight coefficient of the incremental account is increased based on the account number ratio.

[0036] In a second aspect, an embodiment of the present invention provides a commission calculation device for community group purchasing of properties, comprising at least one control processor and a memory for communicating with the at least one control processor; the memory stores instructions executable by the at least one control processor, and the instructions are executed by the at least one control processor so that the at least one control processor can execute the commission calculation method for community group purchasing of properties as described in the first aspect above.

[0037] In a third aspect, an embodiment of the present invention provides an electronic device comprising a commission calculation device for property community group purchasing as described in the second aspect above.

[0038] In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium storing computer-executable instructions, wherein the computer-executable instructions are used to execute the commission calculation method for property community group purchasing as described in the first aspect above.

[0039] The commission calculation method for property community group buying according to an embodiment of the present invention has at least the following beneficial effects: constructing a first group buying event based on a first commodity, constructing a first group buying link in response to a forwarding request for the first group buying event from any first account, and associating the first group buying link to the first account, wherein the first commodity is pre-associated with a plurality of first factors, and each of the first factors is pre-set with a corresponding first coefficient; determining at least one first order generated based on the first group buying link, obtaining first evaluation information of each of the first orders, aggregating first sales data of the first orders, and determining first commission information based on the first sales data and the first coefficient; determining first sentiment classification information corresponding to each of the first evaluation information based on a preset NLP model, and configuring the first factor as a preset text mining factor; The mining category of the model is determined based on the configured text mining model. The first keyword corresponding to each of the first evaluation information is determined, wherein each of the first keywords is associated with a first factor; based on any of the first evaluation information, a target keyword is selected from the first keywords, and the first adjustment score of the first factor associated with the target keyword is determined based on the first sentiment classification information and the target keyword; based on any of the first factors, the second coefficient is determined based on all the first adjustment scores and the corresponding first coefficients, and the second commission information of the first account is determined based on the first sales data and the second coefficient; when the change trend from the first commission information to the second commission information is positively correlated with the first sentiment classification information, the second commission information is determined as the first target commission information. According to the technical solution of the embodiment of the present invention, the first commission information can be calculated with the default coefficient, and then the weight coefficients of each factor are corrected by using the evaluation information of the order, and the first commission information is adjusted to the second commission information based on the first commission information. The application of the second commission information is triggered according to the adjustment direction of the commission information and the positive correlation with the sentiment classification of the comment information, so as to realize the dynamic adjustment of the weight coefficients of different factors and improve the user experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] Figure 1 is a schematic diagram of a property management system provided by an embodiment of the present invention;

[0041] Figure 2 is a flow chart of a method for calculating commissions for property community group purchases provided by another embodiment of the present invention;

[0042] Figure 3 is a complete flow chart of a method for calculating commissions for property community group purchases provided by another embodiment of the present invention;

[0043] Figure 4 This is a structural diagram of a commission calculation device for property community group purchasing provided by another embodiment of the present invention. DETAILED DESCRIPTION

[0044] Embodiments of the present invention are described in detail below, examples of which are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain the present invention, and cannot be understood as limiting the present invention.

[0045] In the description of the present invention, it should be understood that descriptions involving orientations, such as up, down, front, back, left, right, etc., and orientations or positional relationships indicated are based on the orientations or positional relationships shown in the accompanying drawings, and are only for the convenience of describing the present invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be understood as a limitation on the present invention.

[0046] In the description of the present invention, "several" means one or more, "more" means more than two, "greater than", "less than", "exceed" etc. are understood as not including the number itself, and "above", "below", "within" etc. are understood as including the number itself. If there is a description of "first" or "second", it is only used for the purpose of distinguishing the technical features, and cannot be understood as indicating or implying the relative importance or implicitly indicating the number of the indicated technical features or implicitly indicating the order of the indicated technical features.

[0047] In the description of the present invention, unless otherwise clearly defined, terms such as setting, installing, connecting, etc. should be understood in a broad sense, and technicians in the relevant technical field can reasonably determine the specific meanings of the above terms in the present invention based on the specific content of the technical solution.

[0048] An embodiment of the present invention provides a method, device, equipment, and medium for calculating commissions for property community group purchases, wherein the method for calculating commissions for property community group purchases includes: constructing a first group purchase event based on a first commodity, constructing a first group purchase link in response to a forwarding request for the first group purchase event from any first account, and associating the first group purchase link to the first account, wherein the first commodity is pre-associated with a plurality of first factors, and each first factor is pre-set with a corresponding first coefficient; determining at least one first order generated based on the first group purchase link, obtaining first evaluation information of each first order, aggregating first sales data of the first order, and determining first commission information based on the first sales data and the first coefficient; determining first sentiment classification information corresponding to each first evaluation information based on a preset NLP model. information, configure the first factor as the mining category of the preset text mining model, determine the first keyword corresponding to each first evaluation information based on the configured text mining model, wherein each first keyword is associated with a first factor; based on any first evaluation information, select a target keyword from the first keywords, and determine the first adjustment score of the first factor associated with the target keyword based on the first sentiment classification information and the target keyword; based on any first factor, determine the second coefficient based on all the first adjustment scores and the corresponding first coefficient, and determine the second commission information of the first account based on the first sales data and the second coefficient; when the change trend from the first commission information to the second commission information is positively correlated with the first sentiment classification information, determine the second commission information as the first target commission information. According to the technical solution of the embodiment of the present invention, the first commission information can be calculated with the default coefficient, and then the weight coefficients of each factor can be corrected by using the evaluation information of the order, and adjusted to the second commission information based on the first commission information, and the application of the second commission information can be triggered according to the positive correlation between the adjustment direction of the commission information and the sentiment classification of the comment information, so as to realize the dynamic adjustment of the weight coefficients of different factors and improve the user experience.

[0049] The technical solution of the embodiment of the present invention is further described below based on the accompanying drawings.

[0050] Reference Figure 1 , Figure 1 A flowchart of a method for calculating a commission for a property community group purchase provided by an embodiment of the present invention is provided. The method for calculating a commission for a property community group purchase is applied to a property management system. The property management system has multiple preset accounts registered. The method includes but is not limited to the following steps:

[0051] S11, constructing a first group purchase event based on a first product, constructing a first group purchase link in response to a forwarding request for the first group purchase event from any first account, and associating the first group purchase link with the first account, wherein the first product is pre-associated with a plurality of first factors, and each first factor is pre-set with a corresponding first weight coefficient;

[0052] S12, determining at least one first order generated based on the first group purchase link, obtaining first evaluation information of each first order, summarizing first sales data of the first order, and determining first commission information based on the first sales data and a first weight coefficient;

[0053] S13, determining first sentiment classification information corresponding to each first evaluation information based on a preset NLP model, configuring the first factor as a mining category of a preset text mining model, and determining first keywords corresponding to each first evaluation information based on the configured text mining model, wherein each first keyword is associated with a first factor;

[0054] S14, based on any first evaluation information, select a target keyword from the first keywords, and determine a first adjustment score of the first factor associated with the target keyword based on the first sentiment classification information and the target keyword;

[0055] S15, determining a second weight coefficient based on any first factor, based on all first adjustment scores and corresponding first weight coefficients, and determining second commission information of the first account based on the first sales data and the second weight coefficient;

[0056] S16: When the change trend from the first commission information to the second commission information is positively correlated with the first emotion classification information, the second commission information is determined as the first target commission information.

[0057] It should be noted that the management personnel can select any preset product as the first product in the property management system, and construct the first group purchase event by setting the group purchase conditions such as the price and quantity of the first product. The first product and the second product of this embodiment are different products, and the same preset product is selected multiple times and is also collectively defined as the first product; the first group purchase event of this embodiment is a group purchase event initiated based on the first product, and each group purchase event can be distinguished based on the event ID. For example, a group purchase event is initiated again based on the first product, and it is determined to be the second group purchase event due to the different event IDs. The first and second group purchase events will not be repeated later.

[0058] It should be noted that the first group purchase link can be in the form of a common QR code or WeChat link, etc., and no further restrictions are made here.

[0059] It should be noted that the property management system can register multiple preset accounts. After creating the first group purchase event, the link constructed when each account forwards is different. This embodiment associates the first group purchase link with the first account. For example, a QR code is generated based on the first group purchase event and the account ID, so that the QR code carries both the access link of the first group purchase event and the account ID of the first account, ensuring that the first group purchase link can be uniquely matched to a first account in the future, ensuring that the first order generated based on the first group purchase link can correspond to the first account, and distinguishing the orders converted by different preset accounts, thereby adjusting the weight coefficient according to the order situation of each preset account. The first account in this embodiment is the preset account that forwarded the first group purchase event, and will not be repeated in the future.

[0060] For example, Figure 2 As shown, after the first group purchase event is constructed based on product 1-1, group purchase link 1 is generated when account 1 forwards, and group purchase link 2 is generated when account 2 forwards. The property management system can uniquely determine account 1 based on group purchase link 1, and uniquely determine account 2 based on group purchase link 2, so that orders 1-1 to 1-3 generated based on group purchase link 1 are bound to account 1, and similarly, orders 2-1 to 2-3 are bound to account 2.

[0061] It should be noted that the first factor can be set according to actual needs, such as seasonal factors, satisfaction factors, promotion difficulty factors and order conversion rate factors, etc. Each first factor is set with a first weight coefficient. After the first order is generated, the first order is associated with the corresponding first account according to the association relationship between the first group purchase link and the first account, and the first sales data is obtained by simple numerical aggregation. It is well known to those skilled in the art that a certain proportion of conversion is required when calculating the commission based on the first sales data, and the subsequent calculation process of the conversion ratio is not repeated. After the proportion conversion is performed based on the first sales data, the value obtained by multiplying the conversion result and the first weight coefficient is determined as the first commission information. The value of the first weight coefficient can be greater than 1, equal to 1 or less than 1. The user is encouraged to promote by the first weight coefficient with a value greater than 1. For example, a weight coefficient with a larger value is set for the promotion difficulty of a product with greater promotion difficulty, and a first weight coefficient with an initial value of 1 is set for the satisfaction factor. By adjusting downward when calculating the second weight coefficient, users are encouraged to maintain order satisfaction. It can be set according to actual needs. The first and second commission information of this embodiment are used to characterize the calculation stage, rather than the commission information corresponding to a specific account. For example, the first commission information is a value calculated based on the first weight coefficient, and the second commission information is a value calculated based on the adjusted second weight coefficient.

[0062] It is worth noting that not every first factor is related to the comments of the first order. For example, the above-mentioned order conversion rate factor can be calculated based on the number of first orders and the number of forwardings of the first group purchase link. This embodiment does not dynamically adjust all first factors, but only adjusts the first factors that can be associated based on the target keywords.

[0063] For example, Figure 2 As shown, taking account 1 as an example, after sales data 1-1 is calculated based on orders 1-1 to 1-3, the sales data 1-1 is converted according to the conversion ratio, and the commission 1-1 is calculated based on coefficient 1-1, coefficient 1-2 and coefficient 1-3 as the first commission information; for another example, sales data 2-1 calculated by account 2 is different from sales data 1-1 in value. Since they are the same product 1-1, the first factor and the first coefficient are the same. After conversion based on sales data 2-1, commission 2-1 is calculated based on coefficient 1-1, coefficient 1-2 and coefficient 1-3 as the first commission information.

[0064] It should be noted that those skilled in the art are familiar with how to obtain the first evaluation information, and will not go into details here. This embodiment determines the first sentiment classification information of each first evaluation information based on a preset NLP model, and extracts multiple first keywords from the first evaluation information using the first factor as a classification through a text mining model. The NLP model can perform sentiment prediction based on text, and the sentiment classification information can be common user emotions, such as "happy", "normal", "angry", etc., which are not limited here. The text mining model can extract relevant keywords from the text sequence according to the set classification. For example, if the first evaluation information mentions "dissatisfied", it can be determined that the corresponding first factor is a satisfaction factor, and the first keyword is dissatisfied. This embodiment does not involve improvements to the NLP model and the text mining model, and an existing model that can achieve the above functions can be used.

[0065] It should be noted that each first order has a first evaluation information. Therefore, this embodiment determines a first adjustment score based on each first evaluation information. The first emotion classification information is used to indicate whether the first adjustment score is applied positively or reversely. For example, when the first emotion classification information is "happy", the first adjustment score is a positive number. When the first emotion classification information is "angry", the first adjustment score is set to a negative number after determining the value. After traversing each first order, all first adjustment scores of the same factor are summarized, and the first coefficients of each first factor corresponding to the first account are adjusted according to the summarized scores.

[0066] For example, Figure 2As shown, taking the comments of account 1 as an example, the sentiment classification corresponding to order 1-1 is "happy", the sentiment classification corresponding to order 1-2 is "happy", and the sentiment classification corresponding to order 1-3 is "angry". In the seasonal comment 1 of order 1-1, the extracted target keywords are "satisfied" and "product is in season", and the first adjustment score of the satisfaction factor is set to 10 points, and the first adjustment score of the seasonal factor is set to 10 points; in the satisfaction comment 1 of order 1-2, the extracted target keyword is "satisfied", and the first adjustment score of the satisfaction factor is set to 10 points; in the seasonal comment 2 of order 1-3, the extracted target keywords are "dissatisfied" and "product is in season", and the first adjustment score of the satisfaction factor is set to -10 points, and the first adjustment score of the seasonal factor is set to -10 points. For account 1, the adjustment score of the satisfaction factor is 20 points, the adjustment score of the seasonal factor is 0 points, and the adjustment score of the order conversion rate factor is not involved. The coefficient 1-1 is maintained at the current value of 0 points to obtain the coefficient 1-1-1, and the coefficient 1-2 can be increased by 20% with 20 points to obtain the coefficient 1-2-1. Finally, the second commission information is calculated by combining the coefficient 1-1-1, the coefficient 1-2-1 and the unadjusted coefficient 1-3 with the converted first sales data. The specific adjustment score can be set according to actual needs, such as a fixed adjustment of 10 points for each keyword, or setting multiple scores according to the emotional intensity of the keyword. There are no restrictions here, as long as it can achieve the adjustment effect.

[0067] It should be noted that after determining the second commission information, although the second weight coefficient is obtained based on the first evaluation information, the adjustment score of a certain first factor may be set higher, so that the second weight coefficient can be adjusted positively even when the user satisfaction is not high. In this embodiment, the first emotion classification information is used as a judgment on the rationality of the adjustment. For example, the first emotion classification information of each first order is counted. When the number of first emotion classification information representing "happiness" is greater than the number of first emotion classification information representing "anger", and the value of the second commission information is greater than the first commission information, it can be determined that the two are positively correlated, and the commission is paid with the second commission information as the first target commission information; when the number of first emotion classification information representing "happiness" is less than the number of first emotion classification information representing "anger", and the value of the second commission information is greater than the first commission information, it can be determined that the two are negatively correlated, and the adjustment of the second commission information does not meet the user feedback. Therefore, the second commission information obtained this time is discarded, and the first commission information is maintained as the first target commission information.

[0068] In addition, in one embodiment, referring to Figure 3The property management system is preset with a plurality of preset items, each preset item includes a plurality of preset commodities, each preset item is configured with a plurality of preset factors, and each preset factor is configured with a corresponding preset weight coefficient. After step S11, the method further includes but is not limited to the following steps:

[0069] S21, constructing a second group purchase event based on a second commodity of the first project, wherein the first project is a preset project to which the first commodity belongs;

[0070] S22, constructing a second group purchase link in response to a forwarding request for a second group purchase event from any second account, and associating the second group purchase link with the second account;

[0071] S23, determining at least one second order generated based on the second group purchase link, obtaining second evaluation information of each second order, summarizing second sales data of the second order, and determining third commission information based on the second sales data and the first weight coefficient;

[0072] S24, determining the second adjustment score of each first factor based on the NLP model, the text mining model and the second evaluation information, determining the third weight coefficient based on all the second adjustment scores and the first weight coefficient, and determining the second target commission information of the second account based on the third weight coefficient.

[0073] It should be noted that if Figure 2 As shown, the property management system of this embodiment includes multiple preset items, each of which can correspond to a community or a category of goods, such as daily necessities as one item and food as another item. The preset goods in each preset item belong to the same category of goods, and therefore can share the preset factors of the preset items. The preset weight coefficients of the preset factors refer to the first weight coefficient of the above-mentioned first factor, which will not be elaborated here.

[0074] It should be noted that the process and principle of steps S21 to S23 can refer to the description of the first product mentioned above. The second product and the first product belong to the same first project, so the second product is also calculated based on the first coefficient. The second weight coefficient calculated in the above embodiment is based on the first account, and the second product is initiated based on the second account. Although the first account and the second account can be the same preset account for forwarding different links, due to the different products, the second weight coefficient is not applicable to the second product, but is recalculated with the first weight coefficient with reference to the above steps. The specific process will not be repeated here.

[0075] In addition, in one embodiment, referring to Figure 3 After step S24, the method further includes but is not limited to the following steps:

[0076] S25, determining a fourth weight coefficient based on the third weight coefficient and the second weight coefficient;

[0077] S26, associating the fourth weight coefficient with the first account.

[0078] It should be noted that the preset weight coefficient is not adjusted before the second group purchase link is initiated. Starting from the second group purchase event of the same preset item, since there are at least two samples of adjusted weight coefficients, the dynamic adjustment of the preset weight coefficient is triggered by the event construction number being greater than 2, so that each preset weight coefficient of the first item can be more in line with the actual promotion scenario of this type of goods after multiple operations. For example, the fourth weight coefficient can be determined by the average value of the second weight coefficient and the third weight coefficient.

[0079] It should be noted that the fourth weight coefficient is associated with the preset account corresponding to the first account, for example Figure 1 Account 1 is shown, but it does not affect the weight coefficient of account 2. The fourth weight coefficient is obtained based on the evaluation information triggered by the first account, so it cannot represent the promotion performance of account 2. The weight coefficient of each preset account can be iteratively updated independently.

[0080] In addition, in one embodiment, referring to Figure 3 , a relevant connection number is set between every two preset related items. After step S11, the method further includes but is not limited to the following steps:

[0081] S31, constructing a third group purchase event based on the third product of the second project;

[0082] S32: Based on the correlation coefficient between the first item and the second item, update the preset weight coefficient of the second factor corresponding to the third product.

[0083] It should be noted that, in this embodiment, the referenceability of the preset coefficients between different preset items is characterized by the correlation coefficient. For example, group purchase item 1 is food, and group purchase item 2 is beverage. The user overlap corresponding to the two items is relatively high. Therefore, the preset coefficients of the preset factors have a certain reference value. After constructing the third group purchase event based on the third commodity of the second item, the preset weight coefficient of the second factor is first updated according to the correlation coefficient between the first item and the second item, and the commission calculation process of the above embodiment is executed with the updated preset weight coefficient to improve the credibility of the commission calculation.

[0084] For example, the correlation coefficient between group purchase item 1 and group purchase item 2 is set to 1. After constructing the third group purchase event, coefficient 1-1 is multiplied by the correlation coefficient, and the average is calculated with coefficient 2-1 to obtain coefficient 2-1-1. The relevant commission calculation is performed in the third group purchase event using coefficient 2-2-1.

[0085] In addition, in one embodiment, referring to Figure 3 , after step S16, the method further includes:

[0086] S41, determining a preset account that is determined as the first account and not determined as the second account as a third account, and determining a preset account that is determined as both the first account and the second account as a fourth account;

[0087] S42, constructing a fourth group purchase event based on any preset product of the first project, and constructing a fourth group purchase link based on the fourth group purchase event;

[0088] S43, when the third account forwards the fourth group purchase link, determining third target commission information of the third account based on the first weight coefficient;

[0089] S44, when the fourth account forwards the fourth group purchase link, fourth target commission information of the fourth account is determined based on a fourth weight coefficient.

[0090] It should be noted that the first account of this embodiment is a preset account that forwarded the first group purchase link, and the second account is a preset account that forwarded the second group purchase link. In community group purchases, each preset account can forward any group purchase link, so the first account and the second account can be the same preset account. On this basis, the fourth account has a high degree of participation and has forwarded multiple group purchase links in succession. It is likely to continue the promotion effect of the previous group purchase event. The preset weight coefficient obtained by the current multiple iterations is more in line with the actual performance of the preset account. If the third account does not forward continuously, it is difficult to ensure that the previous promotion effect is continued when forwarding the fourth group purchase link. This embodiment reapplies the default first weight coefficient for commission calculation. Of course, the number of intervals can also be adjusted according to actual needs, such as setting it to reset to the first weight parameter after not participating in N consecutive group purchase events. No further restrictions are made here.

[0091] In addition, in one embodiment, referring to Figure 3 Step S14 includes but is not limited to the following steps:

[0092] S141, determining second sentiment classification information of each target keyword based on the NLP model;

[0093] S142, when the first emotion classification information is the same as the second emotion classification information, determining a preset first score as a first adjustment score;

[0094] S143: When the first emotion classification information is different from the second emotion classification information, a preset second score is determined as a first adjustment score, wherein the second score is smaller than the first score.

[0095] It should be noted that the NLP model can output sentiment classification results based on the input text. This embodiment determines the second sentiment classification information of the target keyword based on each NLP model, characterizes the overall sentiment of the first evaluation information through the first sentiment classification information, and further refines the sentiment of the target keyword through the second sentiment classification information, ensuring that user evaluations can be analyzed more accurately.

[0096] It should be noted that when the first emotion classification information is the same as the second emotion classification information, the target keyword can be determined to be a statement, the first factor corresponding to the target keyword is similar to the overall emotion of the user, the credibility of the target keyword is higher, and the first score with a larger value is determined as the first adjustment score. When the first emotion classification information is different from the second emotion classification information, the first factor corresponding to the target keyword is opposite to the overall emotion of the user, and the second score with a smaller value is used as the first adjustment score, so that the first adjustment score is based on the first emotion classification information, and is adjusted twice based on each target keyword.

[0097] Exemplarily, the target keywords include "satisfied" and "out of season", and the first sentiment classification information represents "happy", then the user of the first order is satisfied with the first group buying event, and the NLP model is used to determine that the target keyword "satisfied" represents "happy", and that the target keyword "out of season" represents "unhappy", and the first adjustment score of the seasonal factor is determined to be the second score of 10 points, and the first adjustment score of the satisfaction factor is determined to be the first score of 20 points.

[0098] In addition, in one embodiment, referring to Figure 3 , the number of the first account is multiple, before step S16, the method further includes:

[0099] S51, determining an increasing account and a decreasing account from a plurality of first accounts, and determining an account quantity ratio of the increasing account to the decreasing account, wherein the second weight coefficient of the increasing account is greater than the first weight coefficient, and the second weight coefficient of the decreasing account is less than the first weight coefficient;

[0100] S52, when the account number ratio is greater than one, reducing the second weight coefficient of the decreasing account based on the account number ratio;

[0101] S53, when the account number ratio is less than one, increasing the second weight coefficient of the incremental account based on the account number ratio.

[0102] It should be noted that, according to the description of the above embodiment, when the first emotion classification information represents negative emotions, the first adjustment score is a negative number, and therefore the second weight coefficient may be smaller than the first weight coefficient, resulting in a reduction in the commission information of the first account with poor promotion effect. In this case, this embodiment distinguishes between increasing accounts and decreasing accounts based on the size of the second weight coefficient and the first weight coefficient. The increasing account has a better promotion effect, so the second weight coefficient is increased on the basis of the first weight coefficient. The decreasing account has a poor promotion effect, so the second weight coefficient is decreased on the basis of the first weight coefficient.

[0103] It should be noted that when the account number ratio is greater than one, it can be determined that the first product is less difficult to promote, and most of the first accounts can get good user reviews. At this time, it can be determined that the promotion effect of the decreasing accounts is poor. Based on the account number ratio, the second weight coefficient is further reduced, so that the second weight coefficient better reflects the commission reduction caused by poor promotion effect in the group purchase event that is easy to promote. Since the account number ratio is greater than one, the second weight coefficient can be divided by the account number ratio to achieve a decrease.

[0104] It should be noted that when the account number ratio is less than one, it can be determined that the first product is difficult to promote. In this embodiment, the second weight coefficient of the incremental account is further increased by the account number ratio, and additional incentives are given to the incremental account that has made more promotion operations, so that the second weight coefficient can better reflect the additional benefits generated by the better promotion effect in the group purchase event that is difficult to promote. Since the account number ratio is less than one, the second weight coefficient can be divided by the account number ratio to achieve incremental increase.

[0105] like Figure 4 As shown, Figure 4 : is a structural diagram of a commission calculation device for property community group purchase provided by an embodiment of the present invention. The present invention also provides a commission calculation device for property community group purchase, including:

[0106] The processor 401 may be implemented by a general-purpose central processing unit (CPU), a microprocessor, an application-specific integrated circuit (ASIC), or one or more integrated circuits, and is used to execute relevant programs to implement the technical solutions provided in the embodiments of the present application;

[0107] The memory 402 can be implemented in the form of a read-only memory (ROM), a static storage device, a dynamic storage device, or a random access memory (RAM). The memory 402 can store an operating system and other applications. When the technical solution provided in the embodiment of this specification is implemented by software or firmware, the relevant program code is stored in the memory 402, and the processor 401 calls and executes the commission calculation method for property community group purchase in the embodiment of this application;

[0108] Input / output interface 403, used to implement information input and output;

[0109] Communication interface 404, used to realize communication interaction between the device and other devices, which can be realized through wired mode (such as USB, network cable, etc.) or wireless mode (such as mobile network, WI FI, Bluetooth, etc.);

[0110] Bus 405 , which transmits information between various components of the device (e.g., processor 401 , memory 402 , input / output interface 403 , and communication interface 404 );

[0111] The processor 401 , the memory 402 , the input / output interface 403 and the communication interface 404 are connected to each other in communication within the device via the bus 405 .

[0112] An embodiment of the present application also provides an electronic device, including the commission calculation device for property community group purchasing as described above.

[0113] An embodiment of the present application also provides a storage medium, which is a computer-readable storage medium and stores a computer program. When the computer program is executed by a processor, it implements the above-mentioned commission calculation method for property community group purchasing.

[0114] As a non-transient computer-readable storage medium, the memory can be used to store non-transient software programs and non-transient computer executable programs. In addition, the memory may include a high-speed random access memory, and may also include a non-transient memory, such as at least one disk storage device, a flash memory device, or other non-transient solid-state storage devices. In some embodiments, the memory may optionally include a memory remotely arranged relative to the processor, and these remote memories may be connected to the processor via a network. Examples of the above-mentioned networks include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and a combination thereof. The device embodiments described above are merely schematic, wherein the units described as separate components may or may not be physically separated, and are implemented to be located in one place, or may also be distributed to multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the present embodiment.

[0115] It will be appreciated by those skilled in the art that all or some of the steps and systems in the disclosed method above may be implemented as software, firmware, hardware and appropriate combinations thereof. Some physical components or all physical components may be implemented as software executed by a processor, such as a central processing unit, a digital signal processor or a microprocessor, or may be implemented as hardware, or may be implemented as an integrated circuit, such as an application specific integrated circuit. Such software may be distributed on a computer-readable medium, which may include a computer storage medium (or a non-transitory medium) and a communication medium (or a temporary medium). As known to those skilled in the art, the term computer storage medium includes volatile and non-volatile, removable and non-removable media implemented in any method or technology for storing information (such as computer-readable instructions, data structures, program modules or other data). Computer storage media include, but are not limited to, RAM, ROM, EEPROM, flash memory or other memory technologies, CD-ROM, digital versatile disks (DVD) or other optical disk storage, magnetic cassettes, magnetic tapes, disk storage or other magnetic storage devices, or any other medium that may be used to store desired information and may be accessed by a computer. Furthermore, it is well known to those skilled in the art that communication media typically include computer readable instructions, data structures, program modules, or other data in a modulated data signal such as a carrier wave or other transport mechanism, and may include any information delivery media.

[0116] The above is a specific description of the preferred implementation of the present invention, but the present invention is not limited to the above-mentioned implementation mode. Technical personnel familiar with the field can also make various equivalent deformations or substitutions under the shared conditions without violating the spirit of the present invention. These equivalent deformations or substitutions are all included in the scope defined by the claims of the present invention.

Claims

1. A method for calculating commissions for property community group purchases, characterized in that: Applied to a property management system, the property management system has multiple preset accounts registered, and the method includes: Building a first group purchase event based on a first commodity, building a first group purchase link in response to a forwarding request for the first group purchase event from any first account, and associating the first group purchase link with the first account, wherein the first commodity is pre-associated with a plurality of first factors, and each of the first factors is pre-set with a corresponding first weight coefficient; determining at least one first order generated based on the first group purchase link, obtaining first evaluation information of each of the first orders, summarizing first sales data of the first orders, and determining first commission information based on the first sales data and the first weight coefficient; Determine first sentiment classification information corresponding to each of the first evaluation information based on a preset NLP model, configure the first factor as a mining category of a preset text mining model, and determine first keywords corresponding to each of the first evaluation information based on the configured text mining model, wherein each of the first keywords is associated with one of the first factors; Based on any of the first evaluation information, select a target keyword from the first keywords, and determine a first adjustment score of the first factor associated with the target keyword based on the first sentiment classification information and the target keyword; Based on any of the first factors, determine a second weight coefficient based on all of the first adjustment scores and the corresponding first weight coefficients, and determine second commission information of the first account based on the first sales data and the second weight coefficient; When the change trend from the first commission information to the second commission information is positively correlated with the first emotion classification information, the second commission information is determined as the first target commission information.

2. The method for calculating the commission of community group purchase of properties according to claim 1, characterized in that: The property management system is preset with a plurality of preset items, each of the preset items includes a plurality of preset commodities, each of the preset items is configured with a plurality of preset factors, each of the preset factors is configured with a corresponding preset weight coefficient, and after constructing a first group purchase event based on the first commodity, the method further includes: Building a second group purchase event based on a second commodity of the first item, wherein the first item is the preset item to which the first commodity belongs; In response to a forwarding request for the second group purchase event from any second account, a second group purchase link is constructed, and the second group purchase link is associated with the second account; determining at least one second order generated based on the second group purchase link, obtaining second evaluation information of each second order, summarizing second sales data of the second order, and determining third commission information based on the second sales data and the first weight coefficient; Determine the second adjustment score of each of the first factors based on the NLP model, the text mining model and the second evaluation information, determine the third weight coefficient based on all of the second adjustment scores and the first weight coefficient, and determine the second target commission information of the second account based on the third weight coefficient.

3. The method for calculating the commission of community group purchase of properties according to claim 2, characterized in that: After determining the second target commission information of the second account based on the third weight coefficient, the method further includes: determining a fourth weight coefficient based on the third weight coefficient and the second weight coefficient; The fourth weight coefficient is associated with the first account.

4. The method for calculating the commission of community group purchase of properties according to claim 3, characterized in that: A relevant connection number is set between every two preset related items. After constructing a first group purchase event based on the first commodity, the method further includes: Construct a third group purchase event based on the third product of the second project; Based on the correlation coefficient between the first item and the second item, the preset weight coefficient of the second factor corresponding to the third product is updated.

5. The method for calculating the commission of community group purchase of properties according to claim 4, characterized in that: After determining the second commission information as the first target commission information, the method further includes: Determine the preset account that is determined as the first account and not determined as the second account as a third account, and determine the preset account that is determined as both the first account and the second account as a fourth account; Building a fourth group purchase event based on any preset commodity of the first project, and building a fourth group purchase link based on the fourth group purchase event; When the third account forwards the fourth group purchase link, determining third target commission information of the third account based on the first weight coefficient; When the fourth account forwards the fourth group purchase link, fourth target commission information of the fourth account is determined based on the fourth weight coefficient.

6. The method for calculating the commission of community group purchase of properties according to claim 1, characterized in that: Determining a first adjustment score of the first factor associated with the target keyword based on the first sentiment classification information and the target keyword includes: Determine second sentiment classification information of each of the target keywords based on the NLP model; When the first emotion classification information is the same as the second emotion classification information, determining a preset first score as the first adjustment score; When the first emotion classification information is different from the second emotion classification information, a preset second score is determined as the first adjustment score, wherein the second score is smaller than the first score.

7. The method for calculating the commission of community group purchase of properties according to claim 1, characterized in that: The number of the first accounts is multiple, and before determining the second commission information as the first target commission information, the method further includes: Determine an increasing account and a decreasing account from the plurality of first accounts, and determine an account quantity ratio of the increasing account to the decreasing account, wherein the second weight coefficient of the increasing account is greater than the first weight coefficient, and the second weight coefficient of the decreasing account is less than the first weight coefficient; When the account number ratio is greater than one, reducing the second weight coefficient of the decreasing account based on the account number ratio; Alternatively, when the account number ratio is less than one, the second weight coefficient of the incremental account is increased based on the account number ratio.

8. A commission calculation device for property community group purchase, characterized in that: It includes at least one control processor and a memory for communicating with the at least one control processor; the memory stores instructions that can be executed by the at least one control processor, and the instructions are executed by the at least one control processor so that the at least one control processor can execute the commission calculation method for community group purchasing of properties as described in any one of claims 1 to 7.

9. An electronic device, characterized in that: Including the commission calculation device for property community group purchasing as described in claim 8.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer-executable instructions, and the computer-executable instructions are used to enable a computer to execute the commission calculation method for property community group purchasing as described in any one of claims 1 to 7.

Images