Delivery matching method and device and electronic equipment

Abstract

The invention provides a stock matching method and device and electronic equipment, and relates to the technical field of cargo transportation. The shipping matching method comprises the steps of determining shipping information corresponding to a to-be-matched cargo source, wherein the shipping information comprises the to-be-matched cargo source, a to-be-selected driver corresponding to the to-be-matched cargo source, a first shipping score, a driver cargo source pool and a second shipping score corresponding to the driver cargo source pool; determining the goods source selection probability of each goods source selected by the to-be-selected driver based on the to-be-matched goods source, the first shipping score, the driver goods source pool, the second shipping score and the historical transaction order of the to-be-selected driver; and determining a target driver matched with the to-be-matched goods source from the to-be-selected drivers by taking the maximum sum of the transaction probabilities of the to-be-matched goods source and all goods sources in the driver goods source pool as a target based on the shipping information and the goods source selection probability. According to the scheme, invalid exposure of the goods source can be reduced, and exposure resources of the goods source are saved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of goods transportation, and in particular to a driver-goods matching method and device and electronic equipment. BACKGROUND

[0002] With the development of Internet technology, a digital freight platform emerges as the times require, which can integrate logistics supply and demand resources, provide information sharing of goods, consignors, freight drivers and service providers, and plays an important role in the logistics field. Freight drivers can use the digital freight platform to undertake goods transportation, wherein the matching between the driver and the goods source is an important link, and efficient and reasonable matching between the driver and the goods source is crucial to improve transportation efficiency and reduce costs.

[0003] In the related technology of driver-goods matching, when a driver comes to the freight platform to find goods, the freight platform can match the most suitable goods source to the driver according to a recommendation algorithm, and display these matched goods sources in the form of a list in the interface. However, this matching mechanism is based on the scoring of the goods source, and the higher the score of the high-quality goods source, the more likely it is to be displayed to more drivers, and the goods source is unique, and only one driver can finally transact. This will cause the high-quality goods source to be exposed excessively, resulting in waste of goods exposure resources. SUMMARY

[0004] The present application provides a driver-goods matching method, device and electronic equipment to solve the problem of waste of goods exposure resources caused by the driver-goods matching method in the related art.

[0005] In a first aspect, the present application provides a driver-goods matching method, comprising: determining driver-goods information corresponding to a to-be-matched goods source, wherein the driver-goods information comprises the to-be-matched goods source, a to-be-selected driver corresponding to the to-be-matched goods source, a first driver-goods score, a driver-goods pool, and a second driver-goods score corresponding to the driver-goods pool; determining a goods selection probability of the to-be-selected driver selecting each goods source based on the to-be-matched goods source, the first driver-goods score, the driver-goods pool, the second driver-goods score, and historical transaction orders of the to-be-selected driver; determining a target driver matched with the to-be-matched goods source from the to-be-selected driver based on the driver-goods information and the goods selection probability, with the sum of transaction probabilities of the to-be-matched goods source and all goods sources in the driver-goods pool being maximum as the target.

[0006] Optionally, the determining of the target driver matched with the to-be-matched goods source from the to-be-selected driver based on the driver-goods information and the goods selection probability, with the sum of transaction probabilities of the to-be-matched goods source and all goods sources in the driver-goods pool being maximum as the target, comprises: constructing a target function with a sum of transaction probabilities of the to-be-matched cargo source and all cargo sources in the driver cargo source pool being maximum as a target based on the cargo source information and the cargo source selection probability; taking matching the to-be-matched cargo source to all drivers in the to-be-selected drivers as an initial solution of the target function, subtracting a driver bringing a maximum gain value to the target function in each round of traversal based on the traversal pruning principle until no gain of the target function is produced, and determining the finally reserved driver as a target driver matched with the to-be-matched cargo source.

[0007] Optionally, the taking matching the to-be-matched cargo source to all drivers in the to-be-selected drivers as an initial solution of the target function, subtracting a driver bringing a maximum gain value to the target function in each round of traversal based on the traversal pruning principle until no gain of the target function is produced, and determining the finally reserved driver as a target driver matched with the to-be-matched cargo source comprises: taking matching the to-be-matched cargo source to all drivers in the to-be-selected drivers as an initial solution of the target function, and determining a target function value of the target function based on the initial solution; traversing each solution in the initial solution, and determining a gain value brought to the target function value when the each solution is pruned; determining a maximum gain value in the gain values, and pruning the solution corresponding to the maximum gain value from the initial solution to obtain an updated initial solution; taking the updated initial solution as the initial solution of the target function again until the gain values produced are all less than or equal to 0, determining that no gain of the target function is produced, and determining a driver corresponding to a finally reserved solution in the initial solution as a target driver matched with the to-be-matched cargo source.

[0008] Optionally, the target function is represented as: ; wherein, P i represents a transaction probability of an i-th cargo source, represents a function value of the target function, D represents a set of the to-be-selected drivers, C represents a set of the to-be-matched cargo source and the driver cargo source pool, represents a cargo source selection probability of a j-th driver selecting the i-th cargo source, represents a representation quantity of whether the i-th cargo source is matched to the j-th driver; when , the i-th cargo source is not matched to the j-th driver, and when , the i-th cargo source is matched to the j-th driver.

[0009] Optionally, the determining the cargo source information corresponding to the to-be-matched cargo source comprises: obtain cargo-to-vehicle recall ranking information of the to-be-matched cargo source, drivers in the cargo-to-vehicle recall ranking information being ranked in descending order of matching degree; determine the first preset number of drivers in the cargo-to-vehicle recall ranking information as to-be-selected drivers corresponding to the to-be-matched cargo source, and determine the matching degrees of the to-be-selected drivers in the cargo-to-vehicle recall ranking information as first cargo-to-driver scores of the to-be-selected drivers; obtain a cargo list of the to-be-selected drivers, cargo sources in the cargo list being ranked in descending order of cargo-to-driver matching degree; determine the second preset number of cargo sources in the cargo list as the driver cargo source pool, and determine the cargo-to-driver matching degrees of the cargo sources in the cargo list as second cargo-to-driver scores corresponding to the driver cargo source pool; determine the to-be-matched cargo source, the to-be-selected drivers corresponding to the to-be-matched cargo source and the first cargo-to-driver scores, the driver cargo source pool, and the second cargo-to-driver scores corresponding to the driver cargo source pool as cargo-to-driver information corresponding to the to-be-matched cargo source.

[0010] Optionally, the cargo-to-driver matching method further includes: updating the driver cargo source pool and the second cargo-to-driver scores corresponding to the driver cargo source pool when detecting a cargo searching operation of the to-be-selected driver; deleting a first cargo source from the driver cargo source pool when detecting that the first cargo source is offline and the first cargo source is a cached cargo source in the driver cargo source pool.

[0011] Optionally, the cargo source selection probability of the to-be-selected driver selecting each cargo source is determined based on the to-be-matched cargo source, the first cargo-to-driver scores, the driver cargo source pool, the second cargo-to-driver scores, and historical transaction orders of the to-be-selected driver, and includes: constructing the to-be-matched cargo source and the driver cargo source pool into a cargo list; taking each cargo source in the cargo list as a target cargo source, obtaining a first utility value of the target cargo source being selected and a second utility value of the cargo list not being selected; the first utility value and the second utility value are used to represent the attractiveness of the target cargo source; determining a total expected utility value of all cargo sources in the cargo list based on the first utility values and fitting parameters; determining a first probability that the to-be-selected driver selects a cargo source in the cargo list for transaction and a second probability that the to-be-selected driver does not select a cargo source in the cargo list for transaction based on the fitting parameters, the total expected utility value, and the second utility value; determining a third probability that the target cargo source is selected based on the first utility value of the target cargo source for each of the target cargo sources; determining the cargo source selection probability of each cargo source selected by the to-be-selected driver based on the first probability, the second probability and the third probability; In a case where the target cargo source is the to-be-matched cargo source, the first utility value corresponding to the target cargo source is the first driver-cargo score; in a case where the target cargo source is a cargo source in the driver cargo source pool, the first utility value corresponding to the target cargo source is the second driver-cargo score; and the fitting parameter is determined by maximum log-likelihood estimation on historical driver behavior data.

[0012] Optionally, the determining of the cargo source selection probability of each cargo source selected by the to-be-selected driver based on the first probability, the second probability and the third probability comprises: determining the cargo source selection probability of each cargo source selected by the to-be-selected driver based on the first probability, the second probability and the third probability by using the following formula: ; wherein, denotes the cargo source selection probability of each cargo source selected by the jth to-be-selected driver, denotes the first probability, denotes the second probability, denotes the third probability, denotes the cargo source list, denotes the selection operation of the to-be-selected driver, denotes the selection of no transaction.

[0013] In a second aspect, the present application provides a driver-cargo matching device, comprising: a first determining module configured to determine driver-cargo information corresponding to a to-be-matched cargo source, wherein the driver-cargo information comprises the to-be-matched cargo source, a to-be-selected driver corresponding to the to-be-matched cargo source, a first driver-cargo score, a driver cargo source pool and a second driver-cargo score corresponding to the driver cargo source pool; a second determining module configured to determine a cargo source selection probability of each cargo source selected by the to-be-selected driver based on the to-be-matched cargo source, the first driver-cargo score, the driver cargo source pool, the second driver-cargo score and historical transaction orders of the to-be-selected driver; a third determining module configured to determine a target driver matched with the to-be-matched cargo source from the to-be-selected driver based on the driver-cargo information and the cargo source selection probability, with the sum of transaction probabilities of the to-be-matched cargo source and all cargo sources in the driver cargo source pool being maximized as a target.

[0014] In a third aspect, the present application provides an electronic device, comprising a memory and a processor, wherein the memory stores a computer program capable of running on the processor, and the processor executes the computer program to implement the steps of the freight-matching method according to any one of the first aspect.

[0015] In a fourth aspect, the present application provides a computer-readable storage medium, which stores a computer program, and the computer program is executed by a processor to implement the steps of the freight-matching method according to any one of the first aspect.

[0016] The freight-matching method, device and electronic device provided by the present application can determine the freight information corresponding to the to-be-matched freight source, which includes the to-be-matched freight source, the to-be-selected driver corresponding to the to-be-matched freight source and the first freight score, the driver freight pool and the second freight score corresponding to the driver freight pool, then determine the freight source selection probability of the to-be-selected driver selecting each freight source based on the to-be-matched freight source, the first freight score, the driver freight pool, the second freight score and the historical transaction order of the to-be-selected driver, and then determine the target driver matched with the to-be-matched freight source from the to-be-selected driver based on the freight information and the freight source selection probability, so that the target driver matched with the to-be-matched freight source can be determined from the to-be-selected driver with the maximum transaction amount of all freight sources as the target, when the driver comes to the freight platform to find freight, the to-be-matched freight source can be exposed only in the freight source recommendation list of the matched target driver, and other drivers will not see the to-be-matched freight source, thereby reducing invalid exposure and saving exposure resources of the freight source. BRIEF DESCRIPTION OF DRAWINGS

[0017] Figure 1 A flowchart of the freight-matching method provided by the embodiment of the present application is shown in the figure; Figure 2 A structural diagram of the freight-matching device provided by the embodiment of the present application is shown in the figure. DETAILED DESCRIPTION

[0018] In this application, "at least one" means one or more, and "multiple" means two or more. The association relationship of "and / or" describes the associated objects, which means that there can be three kinds of relationships, for example, A and / or B can represent the following three cases: A exists alone, A and B exist together, and B exists alone. Wherein A and B can be singular or plural. The character " / " generally represents an "or" relationship between the front and rear associated objects. "At least one of the following" or similar expressions means any combination of these items, including single item or any combination of multiple items. For example, at least one of a, b or c alone can represent: a alone, b alone, c alone, combination of a and b, combination of a and c, combination of b and c, or combination of a, b and c. Wherein a, b and c can be single or multiple. In addition, the terms "first", "second" are only for descriptive purposes, and cannot be understood as indicating or implying relative importance.

[0019] The matching between the driver and the cargo source (i.e., driver-cargo matching) is an important part of the freight platform, and efficient and reasonable matching between the driver and the cargo source is crucial to improving transportation efficiency and reducing costs.

[0020] In the related art, when the driver comes to the freight platform to find the cargo, the freight platform can match the most suitable cargo source to the driver according to the recommendation algorithm, and display these matched cargo sources in the form of a list in the interface. However, this matching mechanism is based on the scoring of the cargo source, and the higher the score of the high-quality cargo source, the more likely it is to be displayed to more drivers. Since the cargo source is unique, only one driver can eventually transact. This will cause the high-quality cargo source to be exposed too much, not only wasting the exposure resources of the cargo source, but also creating a clear contrast with the remaining ordinary cargo sources in the driver's cargo list, causing mutual influence between the cargo sources, making it difficult for other ordinary cargo sources to be accepted by the driver, and thus affecting the transportation of goods. Therefore, it is necessary to further optimize the strategy of driver-cargo matching from a more comprehensive perspective.

[0021] In the related art, the orders in a time window can be cached, and then the optimal decision of vehicle-cargo matching is made with the current idle driver as the target of maximizing the transaction volume, and then the orders are dispatched according to the decision result. However, this method is only suitable for scenarios where orders are relatively dense and dispatching does not need to consider the comparison between cargo sources, and requires the platform to have high control over the drivers. However, for the scenario of goods transportation, due to the sparseness of the space-time distribution of the cargo source and the high timeliness requirement of the cargo source being accepted, it is impossible to achieve centralized allocation of the cargo source, and the sparseness of the space-time distribution of the cargo source also determines that the driver mainly performs autonomous order acceptance by listing the cargo source, making it difficult to dispatch orders. Therefore, this vehicle-cargo matching strategy is not suitable for the driver-cargo matching scenario of goods transportation.

[0022] Based on this, the embodiment of the present application provides a new driver and cargo matching method, when a new cargo is issued, a target driver matched with the new cargo can be determined from the drivers to be selected, with the goal of maximizing the transaction volume of all cargos. When a driver comes to the cargo platform to find cargos, the new cargo to be matched can be exposed only in the cargo recommendation list of the target driver matched, and other drivers will not be able to see the new cargo to be matched, thereby reducing invalid exposure, saving exposure resources of the cargos, avoiding unnecessary comparison between cargos, reducing the mutual influence between cargos, and ensuring that all types of cargos can be normally transported.

[0023] The driver and cargo matching method provided by the embodiment of the present application can be applied to an electronic device, and can also be applied to a driver and cargo matching device provided in the electronic device. The driver and cargo matching device can be implemented by software, hardware, or a combination of both. The electronic device can include at least one of a server, a mobile phone, a computer, a vehicle terminal, a tablet computer, a wearable device, and the like, but is not limited thereto. The server can include at least one of a stand-alone server, a virtual server, and a cluster server, but is not limited thereto.

[0024] In the following, the driver and cargo matching method is described in detail. Figure 1 The driver and cargo matching method provided by the embodiment of the present application is described in detail.

[0025] Figure 1 The flowchart of the driver and cargo matching method provided by the embodiment of the present application is shown, and the driver and cargo matching method can include the following steps 110-130. Figure 1

[0026] Step 110: Determine the driver and cargo information corresponding to the cargo to be matched, which includes the cargo to be matched, the driver to be selected corresponding to the cargo to be matched, the first driver and cargo score, the driver cargo pool, and the second driver and cargo score corresponding to the driver cargo pool.

[0027] The cargo to be matched is a new cargo to be issued. The driver to be selected is the driver who wants the new cargo most, which can be determined according to the cargo-finding vehicle recall sorting information of the cargo to be matched, for example, the top N (N is a positive integer) drivers with higher matching degree are determined as the driver to be selected. The driver cargo pool is used to save other cargos that the driver to be selected wants most except the cargo to be matched. It can be understood that these cargos are the cargos that are most likely to be displayed in the cargo list at the same time as the new cargo, which can be determined according to the finding list of all cargo-finding drivers in a preset time period, for example, the top M (M is a positive integer) cargos with higher frequency are cached to form the driver cargo pool.

[0028] ​The first driver-goods score is used to represent the matching degree of the to-be-matched goods source and the to-be-selected driver, and the second driver-goods score is used to represent the matching degree of the to-be-selected driver and each goods source in the driver-goods source pool.

[0029] Specifically, step 110 can be implemented through steps 111-115 as follows.

[0030] Step 111: Obtain the goods-to-car recall ranking information of the to-be-matched goods source. The drivers in the goods-to-car recall ranking information are ranked in descending order of matching degree.

[0031] When a to-be-matched goods source (i.e., new goods) is published on the freight platform, the goods-to-car recall information corresponding to the to-be-matched goods source can be determined according to the preset goods-to-car recall condition. The goods-to-car recall information can include driver information and the matching degree of the driver and the to-be-matched goods source, and then the goods-to-car recall information can be sorted in descending order of matching degree to obtain the goods-to-car recall ranking information.

[0032] For example, the preset goods-to-car recall condition can include: driver information of drivers within a preset range of the to-be-matched goods source, distances between the locations of these drivers and the to-be-matched goods source, destination information of the to-be-matched goods source, city information of cities frequently traveled by these drivers, vehicle types and lengths required by the to-be-matched goods source, vehicle types and lengths of these drivers, volume and weight of the to-be-matched goods source, and vehicle load information of these drivers. Based on this information, the electronic device can analyze the matching degree of the to-be-matched goods source in different dimensions of driver-goods matching, for example, the closer the distance between the location of the driver and the to-be-matched goods source, the higher the matching degree, the more similar the vehicle type and length of the driver and the vehicle type and length required by the to-be-matched goods source, the higher the matching degree, and the more suitable the volume and weight of the to-be-matched goods source and the vehicle load information of the driver, the higher the matching degree. The electronic device can consider the matching degree in these different dimensions comprehensively, integrate the matching degree in these different dimensions using algorithms such as weighted summation, and determine the matching degree of the driver and the to-be-matched goods source.

[0033] Step 112: Determine the first preset number of drivers in the goods-to-car recall ranking information as the to-be-selected drivers corresponding to the to-be-matched goods source, and determine the matching degree corresponding to each to-be-selected driver in the goods-to-car recall ranking information as the first driver-goods score of each to-be-selected driver.

[0034] The first preset number can be set according to actual application, such as 5, 8, 10, etc., which is not specially limited in the present application.

[0035] In the recall order information of the car finding the car, the first N (N is a positive integer) drivers can be determined as the to-be-selected drivers, and these to-be-selected drivers are the drivers with higher matching degrees with the to-be-matched freight sources, and it can be confirmed that they are the drivers who most want to transport the to-be-matched freight sources. For each to-be-selected driver, the matching degree thereof can be determined as the corresponding first driver-freight score value, and the higher the first driver-freight score value is, the greater the probability that the corresponding driver undertakes the to-be-matched freight source is.

[0036] Step 113: Obtain the finding freight list of the to-be-selected driver, and the freight sources in the finding freight list are sorted in descending order of the driver-freight matching degrees.

[0037] For each driver who finds freight on the freight transportation platform, the freight transportation platform can display the corresponding finding freight list to the driver, that is, the freight transportation platform can maintain a finding freight list for each driver, and the finding freight list can be updated regularly or irregularly according to the operation of the driver, the update of the freight source, and the like. Based on this, for each to-be-selected driver who finds freight on the freight transportation platform, the finding freight list of the to-be-selected driver can be directly obtained.

[0038] Step 114: Determine the first second preset number of freight sources in the finding freight list as the driver freight source pool, and determine the driver-freight matching degrees of the freight sources in the finding freight list as the second driver-freight score values corresponding to the driver freight source pool.

[0039] The second preset number can be set according to actual application, such as 5, 10, 15, etc., and the present application does not make special limitations thereto.

[0040] For each to-be-selected driver, a driver freight source pool can be maintained for the to-be-selected driver, and the first second preset number of freight sources, such as the first 10 freight sources, sorted at the top of the finding freight list of the to-be-selected driver are cached in the driver freight source pool. These freight sources in the driver freight source pool are the most matched freight sources when the to-be-selected driver finds freight, and these freight sources can be confirmed as the most wanted freight sources of the to-be-selected driver except the to-be-matched freight source.

[0041] In an embodiment, the driver-freight matching method can further include: in the case where the finding freight operation of the to-be-selected driver is detected, updating the driver freight source pool and the second driver-freight score values corresponding to the driver freight source pool.

[0042] Specifically, for each to-be-selected driver, when the to-be-selected driver finds freight on the freight transportation platform each time, the electronic device can detect the finding freight operation of the to-be-selected driver through the freight transportation platform, such as detecting the operation of calling out the finding freight page. At this time, the electronic device can obtain the first second preset number of freight sources in the finding freight list of the to-be-selected driver within the preset time period before the current time, and update the freight sources in the driver freight source pool of the to-be-selected driver to the first second preset number of freight sources obtained at this time, so as to refresh the cached freight sources and the corresponding second driver-freight score values in the driver freight source pool.

[0043] In this way, the driver source pool can cache the source, so as to meet the timeliness of the source and avoid hiding the source.

[0044] In an embodiment, the driver-source matching method can further include: in the case that the first source is offline and the first source is a source cached in the driver source pool, deleting the first source from the driver source pool.

[0045] Specifically, the source published on the freight platform is in a dynamic state and may be offline at a certain moment, such as being accepted or withdrawn by the owner. For a certain source, when the source is offline, if the source is cached in the driver source pool, it is deleted from the driver source pool at the same time. In this way, the timeliness of the cached source in the driver source pool can be ensured.

[0046] Step 115: determining the to-be-matched source, the to-be-selected driver corresponding to the to-be-matched source and the first driver-source score, the driver source pool, and the second driver-source score corresponding to the driver source pool as the driver-source information corresponding to the to-be-matched source.

[0047] After determining the to-be-selected driver corresponding to the to-be-matched source and the first driver-source score, the driver source pool, and the second driver-source score corresponding to the driver source pool, the to-be-matched source, the to-be-selected driver corresponding to the to-be-matched source and the first driver-source score, the driver source pool, and the second driver-source score corresponding to the driver source pool can be determined as the driver-source information corresponding to the to-be-matched source. For example, these information can be formed into a driver-source matrix and represented in the form of a matrix. The driver-source information can represent all drivers who want the to-be-matched source most and the remaining sources that these drivers want.

[0048] Step 120: determining the source selection probability of each source selected by the to-be-selected driver based on the to-be-matched source, the first driver-source score, the driver source pool, the second driver-source score, and the historical transaction orders of the to-be-selected driver.

[0049] After determining the driver-source information corresponding to the to-be-matched source, the to-be-matched source, the first driver-source score, the driver source pool, and the second driver-source score in the driver-source information, and the historical transaction orders of the to-be-selected driver can be used to determine the source selection probability of each source selected by the to-be-selected driver by using the principle of the Nested Multinomial Logit (NMNL) model.

[0050] Whether the to-be-selected driver transacts the source can be regarded as a two-stage decision. The to-be-selected driver can first decide whether to select the source in the source list, and then decide which source to select.

[0051] Based on this, for any one selection of the jth to-be-selected driver The source selection probability of the goods source can be expressed as formula (1) as follows: (1) Wherein, represents the source selection probability of each goods source selected by the jth driver to be selected, represents a goods source list, and o represents a selection operation of the driver to be selected, represents that no transaction is selected, represents a first probability that the driver to be selected selects a goods source in the goods source list to make a transaction, represents a second probability that the driver to be selected does not select a goods source in the goods source list to make a transaction, represents a third probability that the driver to be selected selects a goods source selected by the selection operation o in the goods source list.

[0052] According to the principle shown in formula (1), in an embodiment, step 120 determines the source selection probability of each goods source selected by the driver to be selected based on the matched goods source, the first driver-goods score, the driver goods pool, the second driver-goods score, and the historical transaction order of the driver to be selected, which can be implemented by steps 121-126 as follows.

[0053] Step 121: Construct the matched goods source and the driver goods pool into a goods source list.

[0054] The driver to be selected is the driver who wants the matched goods source most. For each driver to be selected, the corresponding driver goods pool is the most matched goods source of the driver to be selected when looking for goods, except for the matched goods source. The matched goods source and the driver goods pool can be constructed into a goods source list of the driver to be selected.

[0055] Step 122: Take each goods source in the goods source list as a target goods source, and obtain a first utility value of the target goods source being selected and a second utility value of the goods source list not being selected.

[0056] Wherein, the first utility value and the second utility value are used to represent the attractiveness or value of the target goods source. The higher the first utility value, the higher the attractiveness of the target goods source, and the greater the probability of being selected. The higher the second utility value, the smaller the attractiveness of each target goods source in the goods source list, and the smaller the probability of the target goods source being selected.

[0057] Specifically, the goods source list includes the matched goods source and the goods source in the driver goods pool. In the case that the target goods source is the matched goods source, the first utility value corresponding to the target goods source is the first driver-goods score. In the case that the target goods source is the goods source in the driver goods pool, the first utility value corresponding to the target goods source is the second driver-goods score.

[0058] The second utility value of the to-be-selected driver not selecting the freight source in the freight source list can be determined according to historical transaction orders of the to-be-selected driver, for example, can be the average value of the utility values of the historical transaction orders. Specifically, the second utility value can be determined according to formula (2) as follows: (2) wherein, the second utility value, m represents the number of historical transaction orders, the jth to-be-selected driver kth historical transaction order and the jth to-be-selected driver freight matching degree, that is, the utility value.

[0059] Step 123: determining the total expected utility value of all freight sources in the freight source list based on the first utility value and the fitting parameter.

[0060] wherein, the fitting parameter is determined by maximum log-likelihood estimation of historical driver behavior data. The historical driver behavior data can include information that the driver has transacted the transaction freight source in the historical freight source list, information of non-transacted freight sources that have not been transacted, and freight matching degree between the driver and the freight sources.

[0061] Specifically, the fitting parameter can be determined by the log of the likelihood function shown in formula (3) as follows: (3) wherein, the likelihood function, the fitting parameter; whether the driver and the freight source transact, which can be determined based on the driver information and the corresponding transaction freight source and non-transacted freight source information in the historical driver behavior data, when , it indicates transaction; when , it indicates non-transaction; D represents a set of to-be-selected drivers; the freight source selection probability, the freight source list, the selection operation of the to-be-selected driver, the non-transaction selection.

[0062] After obtaining the fitting parameter and the first utility value of each freight source in the freight source list, the total expected utility value of all freight sources in the freight source list can be determined according to formula (4) as follows: (4) wherein, the total expected utility value, the freight source list, i represents the ith freight source in the freight source list, the first utility value.

[0063] Step 124: Based on the fitting parameter, the total expected utility value and the second utility value, a first probability that the to-be-selected driver selects the goods source in the goods source list to make a deal and a second probability that the to-be-selected driver does not select the goods source in the goods source list to make a deal are determined.

[0064] The fitting parameter is determined The total expected utility value is determined The second utility value is determined After the fitting parameter The total expected utility value And the second utility value , the first probability that the to-be-selected driver selects the goods source in the goods source list to make a deal can be determined according to formula (5) as follows: (5) Wherein, The first probability that the to-be-selected driver selects the goods source in the goods source list to make a deal is represented.

[0065] The second probability that the to-be-selected driver does not select the goods source in the goods source list to make a deal can be determined according to formula (6) as follows: (6) Wherein, The second probability that the to-be-selected driver does not select the goods source in the goods source list to make a deal is represented.

[0066] Step 125: For each target goods source, a third probability that the target goods source is selected is determined based on the first utility value of the target goods source.

[0067] Specifically, for each target goods source, the third probability that the target goods source is selected can be determined according to formula (7) as follows based on the first utility value of the target goods source: (7) Wherein, The third probability that the target goods source is selected is represented, The first utility value of the i-th target goods source in the goods source list is represented.

[0068] Step 126: Based on the first probability, the second probability and the third probability, a goods source selection probability that the to-be-selected driver selects each goods source is determined.

[0069] Specifically, after the first probability, the second probability and the third probability are determined, the goods source selection probability that the to-be-selected driver selects each goods source can be determined according to formula (1) as described above.

[0070] Thus, by using the NMNL model principle to determine the probability of the to-be-selected driver selecting each source based on the to-be-matched source in the driver-source information, the first driver-source score, the driver-source pool and the second driver-source score and the historical transaction orders of the to-be-selected driver, the selection behavior of the to-be-selected driver can be quantified, the mutual influence between the sources is considered, and the coupling problem of "exposing the source set affecting the selection probability" is avoided.

[0071] Step 130: Based on the driver-source information and the source selection probability, a target driver matched with the to-be-matched source is determined from the to-be-selected drivers, with the sum of the transaction probabilities of the to-be-matched source and all sources in the driver-source pool being maximum.

[0072] After determining the driver-source information and the source selection probability of each source in the to-be-selected driver source list, a target function can be established based on the driver-source information and the source selection probability, with the sum of the transaction probabilities of the to-be-matched source and all sources in the driver-source pool being maximum, and a target driver matched with the to-be-matched source is determined from the to-be-selected drivers by optimizing and solving the target function. In this way, when a driver comes to the freight platform to find goods, the to-be-matched source can be exposed only in the source recommendation list of the matched target driver, and other drivers will not be able to see the to-be-matched source, thereby reducing invalid exposure and saving exposure resources of the source.

[0073] Specifically, step 130 determines a target driver matched with the to-be-matched source from the to-be-selected drivers based on the driver-source information and the source selection probability, with the sum of the transaction probabilities of the to-be-matched source and all sources in the driver-source pool being maximum, which can be achieved through steps 131-132 as follows.

[0074] Step 131: Based on the driver-source information and the source selection probability, a target function is constructed with the sum of the transaction probabilities of the to-be-matched source and all sources in the driver-source pool being maximum.

[0075] Specifically, the to-be-matched source and all sources in the driver-source pool can form a source list. After obtaining the driver-source information and the source selection probability, for the i-th source in the source list, the transaction probability of the i-th source can be determined based on the source selection probability of the to-be-selected driver selecting the source according to the following formula (8): (8) where P i represents the transaction probability of the i-th source, D represents the set of to-be-selected drivers, represents the source selection probability of the j-th driver selecting the i-th source, represents the representation of whether the i-th source is matched to the j-th driver; when represents that the i-th source is not matched to the j-th driver, and when Xi,j represents the i-th cargo source matching to the j-th driver.

[0076] Further, the transaction probability of each cargo source in the cargo source list can be summed to obtain the sum of transaction probabilities of all cargo sources, and then a target function is constructed with the goal of maximizing the sum of transaction probabilities, and the constructed target function can be expressed as the following formula (9): (9) Wherein, Xi,j represents the function value of the target function, C represents the set of the driver cargo pool and the to-be-matched cargo source, P i Xi represents the transaction probability of the i-th cargo source, D represents the set of to-be-selected drivers, Xi,j represents the cargo source selection probability of the j-th driver selecting the i-th cargo source, Xi,j represents the representation of whether the i-th cargo source matches to the j-th driver; when Xi,j represents the i-th cargo source not matching to the j-th driver, and when Xi,j represents the i-th cargo source matching to the j-th driver.

[0077] Step 132: taking matching the to-be-matched cargo source to all drivers in the to-be-selected driver as the initial solution of the target function, subtracting the driver bringing the maximum gain value to the target function in each round of traversal by using the traversal pruning principle, until no gain of the target function is produced, and determining the finally reserved driver as the target driver matched with the to-be-matched cargo source. The traversal pruning principle refers to that in the process of each round of traversal of the initial solution, whether the initial solution is pruned from the initial solution set after the end of the round of traversal is determined by judging the influence of the initial solution on the target function after the initial solution is subtracted, so as to optimize and solve the target function.

[0078] Wherein, each solution in the initial solution represents a driver-cargo pair, and is used to represent the matching pair of the to-be-matched cargo source and the to-be-selected driver.

[0079] Specifically, step 132 takes matching the to-be-matched cargo source to all drivers in the to-be-selected driver as the initial solution of the target function, subtracts the driver bringing the maximum gain value to the target function in each round of traversal by using the traversal pruning algorithm, until no gain of the target function is produced, and determines the finally reserved driver as the target driver matched with the to-be-matched cargo source, which can be realized through the following steps 1321~step 1325.

[0080] Step 1321: taking matching the to-be-matched cargo source to all drivers in the to-be-selected driver as the initial solution of the target function, and determining the target function value of the target function based on the initial solution.

[0081] For the to-be-matched cargo source c1, the to-be-matched cargo source c1 can be matched to each driver in the set of to-be-selected drivers D, thereby constructing an initial solution X of the objective function, which can be expressed as formula (10) as follows: (10) Wherein, represents a representation of whether the to-be-matched cargo source c1 is matched to the jth driver in the set of to-be-selected drivers D, represents that the to-be-matched cargo source c1 is matched to the jth driver in the set of to-be-selected drivers D. Then, for the initial solution X, it represents that the to-be-matched cargo source c1 is matched to each driver in the set of to-be-selected drivers D.

[0082] After the initial solution X is constructed, the objective function value of the objective function as shown in formula (9) can be determined according to the initial solution.

[0083] Step 1322: Each solution in the initial solution is traversed to determine the gain value brought to the objective function value when each solution is pruned.

[0084] Each solution in the initial solution represents a driver-cargo pair, and each solution in the initial solution can be regarded as an edge. All edges in the initial solution X are traversed to determine the gain value brought to the objective function value after each edge is pruned .

[0085] For example, assuming that the initial solution X includes 3 solutions, i.e., 3 edges, the first edge can be pruned to determine the objective function value, and the objective function value is compared with the objective function value obtained in step 1321 to obtain the first gain value of the objective function value after the first edge is pruned. Similarly, the second gain value of the objective function value after the second edge is pruned and the third gain value of the objective function value after the third edge is pruned can be obtained.

[0086] Step 1323: The maximum gain value in the gain value is determined, and the solution corresponding to the maximum gain value is pruned from the initial solution to obtain an updated initial solution.

[0087] For example, assuming that the initial solution X includes 3 solutions in step 1322, the first gain value, the second gain value, and the third gain value are obtained, and the maximum gain value is determined therefrom, such as the first gain value. If the first gain value is greater than 0, it indicates that a gain is generated, and at this time, the first edge (i.e., the first solution) corresponding to the first gain value can be pruned from the initial solution to obtain an updated initial solution. At this time, the updated initial solution X includes the remaining 2 solutions.

[0088] Step 1324: The updated initial solution is re-used as the initial solution of the objective function.

[0089] Step 1325: repeat the above steps 1321-1324 until the generated gain values are all less than or equal to 0, then determine that no gain of the target function is generated, and determine the driver corresponding to the final remaining solution in the initial solution as the target driver matched with the to-be-matched freight source.

[0090] For example, as an example of step 1323, the remaining 2 solutions in the initial solution X can be used as the initial solution of the target function again. Then repeat the above steps 1321-1324 until the generated gain values after subtracting each edge are all less than or equal to 0, indicating that no gain of the target function is generated, indicating that the sum of the transaction probabilities of all freight sources in the driver freight source pool reaches the maximum, at this time, the final remaining solution in the initial solution is the optimal solution, and the driver corresponding to each solution is the target driver matched with the to-be-matched freight source. When the driver comes to the freight platform to find freight, the to-be-matched freight source can be exposed only in the freight source recommendation list of these target drivers, and other drivers will not be able to see the to-be-matched freight source, which can effectively reduce the invalid exposure of the to-be-matched freight source and save the exposure resources of the freight source.

[0091] According to the above steps 1321-1325, the principle can be described as follows: Traverse all edges in X, determine the gain value brought by cutting each edge to the target function , then determine the maximum gain value Δmax from these gain values, and obtain the edge corresponding to the maximum gain value Δmax . At this time, it is judged whether Δmax is greater than 0, if yes, it indicates that gain is generated in this round of traversal, and the edge is cut from X at this time, and X is updated to , where , and represents that the driver is subtracted from the set of to-be-selected drivers D. Then, continue to traverse the remaining edges in X, determine the gain value brought by cutting each edge in X to the target function, and continue to determine the maximum gain value Δmax from these gain values, and obtain the edge corresponding to the maximum gain value Δmax. When Δmax is greater than 0, continue to cut the edge from X to update X. Thus, X is updated constantly until Δmax is less than or equal to 0, indicating that no gain of the target function is generated, at this time, the sum of the transaction probabilities of all freight sources in the driver freight source pool reaches the maximum, and the driver finally retained in X can be determined as the target driver matched with the to-be-matched freight source.

[0092] The method for matching a driver and a cargo provided in the embodiments of the present application can determine the driver-cargo information corresponding to the cargo to be matched, the driver-cargo information including the cargo to be matched, the driver to be selected corresponding to the cargo to be matched and a first driver-cargo score, a driver-cargo pool and a second driver-cargo score corresponding to the driver-cargo pool, then determine the cargo selection probability of the driver to be selected selecting each cargo based on the cargo to be matched, the first driver-cargo score, the driver-cargo pool, the second driver-cargo score and the historical transaction order of the driver to be selected, and then determine the target driver matched with the cargo to be matched from the driver to be selected based on the driver-cargo information and the cargo selection probability, with the sum of the transaction probabilities of the cargo to be matched and all the cargos in the driver-cargo pool being maximum as the target. In this way, the target driver matched with the cargo to be matched can be determined from the driver to be selected with the transaction volume of all the cargos being maximized as the target, and when the driver comes to the cargo transportation platform to find cargos, the cargo to be matched can be exposed only in the cargo recommendation list of the target driver matched, and other drivers will not see the cargo to be matched, thereby reducing invalid exposure and saving exposure resources of the cargos. Moreover, unnecessary comparison between cargos is avoided, the mutual influence between cargos is reduced, and all kinds of cargos can be normally transported.

[0093] The method for matching a driver and a cargo provided in the embodiments of the present application can construct the driver-cargo information based on the real-time cached driver-cargo pool, without covering cargos, and can meet the timeliness requirement of the cargos. In addition, the driver-cargo matching decision is made with the transaction volume of all the cargos being maximized as the target, thereby effectively reducing invalid exposure, improving the overall transaction volume and improving the efficiency of the cargo transportation platform.

[0094] The embodiments of the present application further provide a device for matching a driver and a cargo, Figure 2 The structure schematic diagram of the device for matching a driver and a cargo provided in the embodiments of the present application is shown, and referring to Figure 2 The device for matching a driver and a cargo can include: The first determining module 210 is configured to determine the driver-cargo information corresponding to the cargo to be matched, the driver-cargo information including the cargo to be matched, the driver to be selected corresponding to the cargo to be matched and a first driver-cargo score, a driver-cargo pool and a second driver-cargo score corresponding to the driver-cargo pool; The second determining module 220 is configured to determine the cargo selection probability of the driver to be selected selecting each cargo based on the cargo to be matched, the first driver-cargo score, the driver-cargo pool, the second driver-cargo score and the historical transaction order of the driver to be selected; The third determining module 230 is configured to determine the target driver matched with the cargo to be matched from the driver to be selected based on the driver-cargo information and the cargo selection probability, with the sum of the transaction probabilities of the cargo to be matched and all the cargos in the driver-cargo pool being maximum as the target.

[0095] In an embodiment, the third determining module 230 can include: The target function construction unit is configured to construct a target function based on the cargo information and the cargo source selection probability, so that a sum of transaction probabilities of all cargo sources in the driver-cargo source pool to which the cargo source is to be matched is maximized. The target driver determination unit is configured to take all drivers in the to-be-selected drivers to which the to-be-matched cargo source is to be matched as an initial solution of the target function, subtract a driver that brings a maximum gain value to the target function in each round of traversal based on the traversal pruning principle, until no gain of the target function is generated, and determine the finally retained driver as a target driver to which the to-be-matched cargo source is to be matched.

[0096] In an embodiment, the target driver determination unit is specifically configured to: take all drivers in the to-be-selected drivers to which the to-be-matched cargo source is to be matched as an initial solution of the target function, determine a target function value of the target function based on the initial solution; traverse each solution in the initial solution, determine a gain value brought to the target function value when each solution is pruned; determine a maximum gain value in the gain values, and prune the solution corresponding to the maximum gain value from the initial solution to obtain an updated initial solution; take the updated initial solution as the initial solution of the target function again until the generated gain values are all less than or equal to 0, determine that no gain of the target function is generated, and determine a driver corresponding to a finally retained solution in the initial solution as a target driver to which the to-be-matched cargo source is to be matched.

[0097] In an embodiment, the constructed target function can be represented as: ; wherein, P i represents a transaction probability of the ith cargo source, represents a function value of the target function, D represents a set of to-be-selected drivers, and C represents a set of to-be-matched cargo sources, represents a cargo source selection probability of the jth driver selecting the ith cargo source, represents a representation quantity of whether the ith cargo source is matched to the jth driver; when , it represents that the ith cargo source is not matched to the jth driver, and when , it represents that the ith cargo source is matched to the jth driver.

[0098] In an embodiment, the first determination module 210 can include: The first acquisition unit is configured to acquire cargo-finding-vehicle recall sorting information of the to-be-matched cargo source, and the drivers in the cargo-finding-vehicle recall sorting information are sorted in descending order of matching degrees; The first determination unit is configured to determine the first preset number of drivers in the cargo-finding-vehicle recall sorting information as the to-be-selected drivers corresponding to the to-be-matched cargo source, and determine the matching degrees of the to-be-selected drivers in the cargo-finding-vehicle recall sorting information as the first driver-cargo scores of the to-be-selected drivers. The second obtaining unit is configured to obtain a cargo searching list of the to-be-selected driver, and the cargos in the cargo searching list are sorted in descending order of the driver-cargo matching degrees; The second determining unit is configured to determine the first second preset number of cargos in the cargo searching list as the driver cargo pool, and determine the driver-cargo matching degrees of the cargos in the cargo searching list as the second driver-cargo scores corresponding to the driver cargo pool. The third determining unit is configured to determine the to-be-matched cargo, the to-be-selected driver corresponding to the to-be-matched cargo, the first driver-cargo score, the driver cargo pool, and the second driver-cargo scores corresponding to the driver cargo pool as the driver-cargo information corresponding to the to-be-matched cargo.

[0099] In an embodiment, the driver-cargo matching device can further include an updating module configured to update the driver cargo pool and the second driver-cargo scores corresponding to the driver cargo pool when it is detected that the to-be-selected driver performs a cargo searching operation.

[0100] In an embodiment, the driver-cargo matching device can further include a deleting module configured to delete the first cargo from the driver cargo pool when it is detected that the first cargo is offline and the first cargo is a cached cargo in the driver cargo pool.

[0101] In an embodiment, the second determining module 220 can include: The cargo list constructing unit is configured to construct the to-be-matched cargos and the driver cargo pool as a cargo list. The third obtaining unit is configured to obtain, for each cargo in the cargo list as a target cargo, a first utility value of the target cargo being selected and a second utility value of the cargo list not being selected, wherein the first utility value and the second utility value are used to represent the attractiveness of the target cargo. The fourth determining unit is configured to determine a total expected utility value of all cargos in the cargo list based on the first utility values and the fitting parameter. The fifth determining unit is configured to determine, based on the fitting parameter, the total expected utility value, and the second utility value, a first probability that the to-be-selected driver selects a cargo in the cargo list to make a deal and a second probability that the to-be-selected driver does not select a cargo in the cargo list to make a deal. The sixth determining unit is configured to determine, for each target cargo, a third probability that the target cargo is selected based on the first utility value of the target cargo. The seventh determining unit is configured to determine, based on the first probability, the second probability, and the third probability, a cargo selection probability of the to-be-selected driver selecting each cargo. In a case where the target cargo is the to-be-matched cargo, the first utility value corresponding to the target cargo is the first driver-cargo score; in a case where the target cargo is a cargo in the driver cargo pool, the first utility value corresponding to the target cargo is the second driver-cargo score; and the fitting parameter is determined by performing maximum log-likelihood estimation on historical driver behavior data.

[0102] In an embodiment, the seventh determining unit is specifically configured to determine the probability of each freight source selected by the to-be-selected driver based on the first probability, the second probability and the third probability, by using the following formula: ; wherein, denotes the probability of each freight source selected by the jth to-be-selected driver, denotes the first probability, denotes the second probability, denotes the third probability, denotes the freight source list, denotes the selection operation of the to-be-selected driver, denotes the selection of no transaction.

[0103] The driver-freight matching device provided by the embodiments of the present application has the same implementation principles and beneficial effects as the driver-freight matching method provided by the above embodiments, and thus will not be described here.

[0104] The device embodiments described above are only schematic, and the units described as separate components can or can not be physically separate, and the components displayed as units can or can not be physical units, i.e., can be located in one place, or can be distributed on multiple network units. According to actual needs, some or all of the modules can be selected to achieve the purpose of the embodiments of the present application. Those skilled in the art can understand and implement without creative labor.

[0105] The embodiments of the present application also provide an electronic device, including a memory and a processor, the memory stores a computer program capable of running on the processor, and the processor implements the steps of the driver-freight matching method described in any of the above method embodiments when executing the computer program, which will not be described here.

[0106] Based on the driver-freight matching method described in any of the above embodiments, the embodiments of the present application also provide a computer readable storage medium, for example, a non-transitory computer readable storage medium can be a read-only memory (ROM), a random access memory (RAM), a CD-ROM, a magnetic tape, a floppy disk and an optical data storage device, etc. The storage medium stores computer instructions for executing the driver-freight matching method described in any of the above embodiments, which will not be described here.

[0107] Those skilled in the art can understand that all or part of the steps of the above-mentioned embodiments can be completed by hardware, or can be instructed by programs to complete the related hardware, and the programs can be stored in a computer readable storage medium. The storage medium mentioned above can be a read-only memory, a magnetic disk or an optical disk, etc.

[0108] Other embodiments of the application will be apparent to those skilled in the art from consideration of the specification and practice of the application disclosed herein. It is intended that the specification and examples be considered as exemplary only, with the true scope and spirit of the application being indicated by the following claims.

Claims

1. A driver-cargo matching method, characterized in that: include: Determine driver and cargo information corresponding to the cargo source to be matched, wherein the driver and cargo information includes the cargo source to be matched, the to-be-selected driver corresponding to the cargo source to be matched and the first driver and cargo score, a driver cargo source pool, and the second driver and cargo score corresponding to the driver cargo source pool; Determine the cargo source selection probability of the driver to be selected for each cargo source based on the cargo source to be matched, the first driver cargo score, the driver cargo source pool, the second driver cargo score, and the historical completed orders of the driver to be selected; Based on the driver and cargo information and the cargo selection probability, with the goal of maximizing the sum of the transaction probabilities of the cargo to be matched and all cargo sources in the driver's cargo pool, a target driver who matches the cargo to be matched is determined from the drivers to be selected.

2. The driver-cargo matching method according to claim 1, characterized in that: The method of determining a target driver matching the cargo source to be matched from the drivers to be selected based on the driver-cargo information and the cargo source selection probability, with the goal of maximizing the sum of the transaction probabilities of the cargo source to be matched and all cargo sources in the driver's cargo source pool, includes: Based on the driver-cargo information and the cargo selection probability, an objective function is constructed with the goal of maximizing the sum of the transaction probabilities of the cargo source to be matched and all cargo sources in the driver's cargo source pool; The initial solution of the objective function is to match the cargo source to all the drivers among the drivers to be selected. The driver who brings the maximum gain value to the objective function in each round of traversal is subtracted by the traversal pruning principle until no gain of the objective function is generated. The driver finally retained is determined as the target driver matching the cargo source to be matched.

3. The driver-cargo matching method according to claim 2, characterized in that: The method uses all drivers among the drivers to be selected that match the cargo source to be matched as the initial solution of the objective function, and uses the traversal pruning principle to subtract the driver that brings the maximum gain value to the objective function in each round of traversal until no gain of the objective function is generated, and determines the finally retained driver as the target driver that matches the cargo source to be matched, including: Taking matching the cargo source to be matched with all drivers among the drivers to be selected as an initial solution of the objective function, and determining an objective function value of the objective function based on the initial solution; Traversing each solution in the initial solution, and determining a gain value brought to the objective function value when each solution is removed; Determining a maximum gain value among the gain values, and pruning a solution corresponding to the maximum gain value from the initial solution to obtain an updated initial solution; The updated initial solution is used again as the initial solution of the objective function until the generated gain values ​​are all less than or equal to 0, then it is determined that no gain of the objective function is generated, and the driver corresponding to the solution finally retained in the initial solution is determined as the target driver that matches the cargo source to be matched.

4. The driver-cargo matching method according to claim 2, characterized in that: The objective function is expressed as: ； Among them, P i represents the transaction probability of the i-th source of goods, represents the function value of the objective function, D represents the set of drivers to be selected, C represents the set of the driver cargo pool and the cargo sources to be matched, represents the probability of the j-th driver choosing the i-th cargo source, Indicates whether the i-th cargo source is matched to the j-th driver; when When , it means that the i-th cargo source is not matched to the j-th driver. , which means that the i-th cargo source is matched to the j-th driver.

5. The driver-cargo matching method according to any one of claims 1 to 4, characterized in that: Determining the cargo information corresponding to the source of goods to be matched includes: Obtaining cargo-finding vehicle recall sorting information of the cargo source to be matched, and sorting the drivers in the cargo-finding vehicle recall sorting information in descending order of matching degree; Determine the first preset number of drivers in the cargo search vehicle recall sorting information as the drivers to be selected corresponding to the cargo source to be matched, and determine the matching degree corresponding to each of the drivers to be selected in the cargo search vehicle recall sorting information as the first driver-cargo score of each of the drivers to be selected; Obtaining a cargo search list of the driver to be selected, sorting the cargo sources in the cargo search list in descending order of driver-cargo matching degree; Determine the first second preset number of cargo sources in the cargo search list as the driver cargo source pool, and determine the driver-cargo matching degree corresponding to each cargo source in the cargo search list as the second driver-cargo score corresponding to the driver cargo source pool; The cargo source to be matched, the driver to be selected corresponding to the cargo source to be matched and the first driver-cargo score, the driver cargo source pool and the second driver-cargo score corresponding to the driver cargo source pool are determined as the driver-cargo information corresponding to the cargo source to be matched.

6. The driver-cargo matching method according to claim 5, characterized in that: The driver-cargo matching method further includes: When detecting the cargo search operation of the driver to be selected, updating the driver cargo source pool and the second driver cargo score corresponding to the driver cargo source pool; When it is detected that the first source of goods is offline and the first source of goods is a source of goods cached in the driver's source of goods pool, the first source of goods is deleted from the driver's source of goods pool.

7. The driver-cargo matching method according to any one of claims 1 to 4, characterized in that: The determining of the cargo source selection probability of the driver to be selected selecting each cargo source based on the cargo source to be matched, the first driver cargo score, the driver cargo source pool, the second driver cargo score, and the historical completed orders of the driver to be selected includes: Constructing the cargo source to be matched and the driver cargo source pool into a cargo source list; Taking each supply source in the supply source list as a target supply source, obtaining a first utility value of the target supply source being selected and a second utility value of the target supply source not being selected from the supply source list; the first utility value and the second utility value are used to characterize the attractiveness of the target supply source; Determining a total expected utility value of all sources in the source list based on each of the first utility values ​​and the fitting parameter; Determining, based on the fitting parameter, the total expected utility value, and the second utility value, a first probability that the driver to be selected selects a source from the list of sources for transaction and a second probability that the driver to be selected does not select a source from the list of sources for transaction; For each target supply source, determining a third probability of the target supply source being selected based on the first utility value of the target supply source; Determining the cargo source selection probability of the to-be-selected driver selecting each cargo source based on the first probability, the second probability, and the third probability; Among them, when the target cargo source is the cargo source to be matched, the first utility value corresponding to the target cargo source is the first driver cargo score; when the target cargo source is the cargo source in the driver cargo pool, the first utility value corresponding to the target cargo source is the second driver cargo score; the fitting parameters are determined by maximizing the log-likelihood estimation of historical driver behavior data.

8. The driver-cargo matching method according to claim 7, characterized in that: The determining, based on the first probability, the second probability, and the third probability, the cargo source selection probability of the to-be-selected driver selecting each cargo source includes: Based on the first probability, the second probability, and the third probability, the cargo source selection probability of the to-be-selected driver selecting each cargo source is determined using the following formula: ； in, represents the probability of the jth driver to be selected selecting each cargo source, represents the first probability, represents the second probability, represents the third probability, represents the cargo source list, o represents the selection operation of the driver to be selected, Indicates choosing not to trade.

9. A driver-cargo matching device, characterized in that: include: A first determination module is configured to determine driver and cargo information corresponding to a source of cargo to be matched, wherein the driver and cargo information includes the source of cargo to be matched, a to-be-selected driver corresponding to the source of cargo to be matched and a first driver and cargo score, a driver cargo source pool, and a second driver and cargo score corresponding to the driver cargo source pool; A second determination module is configured to determine a cargo source selection probability of the driver to be selected to select each cargo source based on the cargo source to be matched, the first driver cargo score, the driver cargo source pool, the second driver cargo score, and the historical completed orders of the driver to be selected; The third determination module is used to determine a target driver who matches the cargo source to be matched from the drivers to be selected based on the driver-cargo information and the cargo source selection probability, with the goal of maximizing the sum of the transaction probabilities of the cargo source to be matched and all cargo sources in the driver's cargo source pool.

10. An electronic device comprising a memory and a processor, wherein the memory stores a computer program that can be run on the processor, wherein: When the processor executes the computer program, the steps of the driver-cargo matching method according to any one of claims 1 to 8 are implemented.

Images