Store arrival condition determination method and device, computer equipment and storage medium

Abstract

The invention discloses an arrival condition determination method and device, computer equipment and a storage medium, which can be applied to scenes such as cloud technology and artificial intelligence, and the method comprises the following steps: obtaining a detection record of first electronic equipment, the detection record comprising M WIFI identifiers and corresponding M WIFI signal intensities; wIFI features are determined according to the M WIFI identifiers, the M WIFI signal intensities, a first WIFI identifier and a WIFI identifier list, the first WIFI identifier is a WIFI identifier of the target shop, and the WIFI identifier list is a list of WIFI identifiers detected in the target shop; according to the WIFI features, using a target probability model to determine the probability that the object corresponding to the first electronic equipment passes the target shop; and determining the condition that the object arrives at the target shop according to the probability. According to the embodiment of the invention, the detected WIFI identifier and the corresponding WIFI signal strength are used, so that the accuracy of the arrival condition can be improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of computer, more particularly, to a store visit situation determination method and device, computer equipment and storage medium. BACKGROUND

[0002] In order to improve the benefits of physical stores, many store owners of physical stores will choose to attract users in the form of information push. In order to improve the accuracy and flexibility of information push, the information pushed to the user can be determined according to the store visit rate of the user.

[0003] Physical stores generally provide WIFI networks, and the store visit situation of a user corresponding to an electronic device can be determined according to whether the electronic device connects the WIFI network, and the store visit rate of the user can be determined according to the store visit situation of the user. It can be seen that it is very important to accurately determine the store visit situation of the user. However, not every user will connect the WIFI network through the electronic device after visiting the store, which reduces the accuracy of the store visit situation. SUMMARY

[0004] In view of the above problems, the embodiments of the present application propose a store visit situation determination method and device, computer equipment and storage medium to improve the above problems.

[0005] In a first aspect, the embodiments of the present application disclose a store visit situation determination method, comprising:

[0006] obtaining a detection record of a first electronic device, the detection record comprising M WIFI identifiers and M WIFI signal strengths, the M WIFI identifiers and the M WIFI signal strengths corresponding one by one, M being an integer greater than 0;

[0007] determining a WIFI feature according to the M WIFI identifiers, the M WIFI signal strengths, a first WIFI identifier and a WIFI identifier list, the first WIFI identifier being a WIFI identifier of a target store, the WIFI identifier list being a list of WIFI identifiers detected in the target store, and the WIFI identifier list comprising the first WIFI identifier;

[0008] determining a probability that a first object has visited the target store using a target probability model according to the WIFI feature, the first object being an object corresponding to the first electronic device;

[0009] determining a store visit situation of the first object according to the probability that the first object has visited the target store.

[0010] In a second aspect, the embodiments of the present application disclose a store visit situation determination device, comprising:

[0011] The acquisition unit is configured to acquire a detection record of the first electronic device, wherein the detection record comprises M WIFI identifiers and M WIFI signal strengths, the M WIFI identifiers and the M WIFI signal strengths are in one-to-one correspondence, and M is an integer greater than 0;

[0012] The first determination unit is configured to determine a WIFI feature according to the M WIFI identifiers, the M WIFI signal strengths, a first WIFI identifier, and a WIFI identifier list, wherein the first WIFI identifier is a WIFI identifier of a target store, the WIFI identifier list is a list of WIFI identifiers detected in the target store, and the WIFI identifier list comprises the first WIFI identifier.

[0013] The second determination unit is configured to determine a probability that a first object has been to the target store by using a target probability model according to the WIFI feature, wherein the first object corresponds to the first electronic device.

[0014] The third determination unit is configured to determine a condition that the first object has been to the target store according to the probability that the first object has been to the target store.

[0015] As a possible implementation, the WIFI signal strength comprises K strength levels, and K is an integer greater than 1.

[0016] The first determination unit is specifically configured to:

[0017] Determine WIFI identifiers in the M WIFI identifiers that belong to the WIFI identifier list, to obtain N WIFI identifiers, and N is an integer less than or equal to M.

[0018] Determine a detection feature according to detection probabilities corresponding to the N WIFI identifiers.

[0019] Determine a current strength level corresponding to each WIFI signal strength in N WIFI signal strengths according to the K strength levels, to obtain current strength levels corresponding to the N WIFI identifiers, and the N WIFI signal strengths are WIFI signal strengths corresponding to the N WIFI identifiers in the M WIFI signal strengths.

[0020] Determine a strength feature according to a strength probability corresponding to the current strength level corresponding to the N WIFI identifiers and the first WIFI identifier.

[0021] The second determination unit is specifically configured to determine the probability that the first object has been to the target store by using the target probability model according to the detection feature and the strength feature.

[0022] As a possible implementation, the first determining unit determines the detection feature according to the detection probability corresponding to the N WIFI identifiers, including:

[0023] determining the sum of the detection probability corresponding to the N WIFI identifiers, to obtain a first feature;

[0024] determining the average of the detection probability corresponding to the N WIFI identifiers, to obtain a second feature;

[0025] determining the maximum of the detection probability corresponding to the N WIFI identifiers, to obtain a third feature;

[0026] determining the detection feature according to at least one of the first feature, the second feature and the third feature.

[0027] As a possible implementation, the first determining unit determines the intensity feature according to the intensity probability corresponding to the current intensity level corresponding to the N WIFI identifiers and the first WIFI identifier, including:

[0028] determining the sum of the intensity probability corresponding to the current intensity level corresponding to the N WIFI identifiers, to obtain a fourth feature;

[0029] determining the average of the intensity probability corresponding to the current intensity level corresponding to the N WIFI identifiers, to obtain a fifth feature;

[0030] determining the maximum of the intensity probability corresponding to the current intensity level corresponding to the N WIFI identifiers, to obtain a sixth feature;

[0031] determining the WIFI signal intensity of the target store according to the N WIFI signal intensities and the first WIFI identifier, to obtain a seventh feature;

[0032] determining the intensity feature according to at least one of the fourth feature, the fifth feature and the sixth feature, and the seventh feature.

[0033] As a possible implementation, the acquisition unit is further configured to acquire training data, the training data including detection records of a plurality of electronic devices and labels of objects corresponding to the plurality of electronic devices having visited the target store;

[0034] The first determining unit is further configured to determine the detection feature and the intensity feature corresponding to a second electronic device according to the detection records of the second electronic device, the first WIFI identifier and the WIFI identifier list, the second electronic device being any electronic device in the plurality of electronic devices.

[0035] The second determining unit is further configured to determine, according to the detection feature and the intensity feature corresponding to the second electronic device, a predicted probability of a second object passing through the target store by using an initial probability model, the second object being an object corresponding to the second electronic device.

[0036] The apparatus further includes:

[0037] The fourth determining unit is configured to determine a loss value according to the predicted probability of the second object passing through the target store and the label.

[0038] The optimization unit is configured to optimize parameters of the initial probability model according to the loss value to obtain the target probability model.

[0039] As a possible implementation, the apparatus further includes a statistical unit, which is specifically configured to:

[0040] determine a total number of times of an object passing through a store according to the labels corresponding to the plurality of electronic devices;

[0041] determine a first number of times of the object passing through the target store and detecting a second WIFI identifier according to the detection records of the plurality of electronic devices and the labels of the plurality of electronic devices, the second WIFI identifier being any WIFI identifier in the WIFI identifier list;

[0042] determine a second number of times of the object passing through the target store and detecting a target intensity level corresponding to the second WIFI identifier according to the detection records of the plurality of electronic devices and the labels of the plurality of electronic devices, the target intensity level being any intensity level in the K intensity levels;

[0043] determine a detection probability corresponding to the second WIFI identifier according to the first number and the total number of times of the object passing through the store;

[0044] determine an intensity probability corresponding to the target intensity level corresponding to the second WIFI identifier according to the second number and the total number of times of the object passing through the store.

[0045] As a possible implementation, the third determining unit is specifically configured to:

[0046] determine that the first object has passed through the target store in a case where the probability of the first object passing through the target store is greater than or equal to a probability threshold.

[0047] determine that the first object has not passed through the target store in a case where the probability of the first object passing through the target store is less than the probability threshold.

[0048] As a possible implementation, the apparatus further includes:

[0049] a fifth determining unit, configured to determine a store-visit rate of the first object to the target store according to the situation of the first object to the target store;

[0050] The fifth determining unit is further configured to determine target information according to the store-visit rate.

[0051] a sending unit, configured to send the target information to the first electronic device.

[0052] In a third aspect, an embodiment of the present application discloses a computer device, including: a processor; a memory, the memory storing computer readable instructions, when the computer readable instructions are executed by the processor, the method described above is implemented.

[0053] In a fourth aspect, an embodiment of the present application discloses a computer readable storage medium, storing computer readable instructions, when the computer readable instructions are executed by a processor, the method described above is implemented.

[0054] In a fifth aspect, an embodiment of the present application discloses a computer program product, including computer instructions, when the computer instructions are executed by a processor, the method described above is implemented.

[0055] In the embodiment of the present application, the detection record of the first electronic device including M WIFI identifiers and M WIFI signal strengths is acquired, the M WIFI identifiers and the M WIFI signal strengths are one-to-one corresponding; the WIFI feature is determined according to the M WIFI identifiers, the M WIFI signal strengths, the first WIFI identifier and the WIFI identifier list, the first WIFI identifier is the WIFI identifier of the target store, the WIFI identifier list is the list of the WIFI identifiers detected in the target store, and the WIFI identifier list includes the first WIFI identifier; the probability of the first object to the target store corresponding to the first electronic device is determined according to the WIFI feature using the target probability model; and the situation of the first object to the target store is determined according to the probability of the first object to the target store. In the case that the WIFI of the electronic device is turned on, the electronic device will automatically detect the WIFI network around. The position of the electronic device is different, and the detected WIFI identifier and the corresponding WIFI signal strength can be different. Therefore, the user store-visit situation is determined according to the detected WIFI identifier and the corresponding WIFI signal strength, and the accuracy of the store-visit situation can be improved. BRIEF DESCRIPTION OF DRAWINGS

[0056] The accompanying drawings, which are incorporated herein and form a part of the specification, illustrate embodiments consistent with the present application and, together with the description, further serve to explain the principles of the application. It is to be understood that the drawings are designed solely for purposes of illustration to be used in conjunction with the description. It is to be understood that the drawings are designed solely for purposes of illustration and to aid in the understanding of the principles of the application, and that, accordingly, they are not to scale with one another; nor are the drawings to be interpreted as a definition of the limits of the application as set forth in the appended claims.

[0057] Figure 1 is a structural schematic diagram of a network architecture disclosed by embodiments of the present application;

[0058] Figure 2 is a flow schematic diagram of a store situation determination method disclosed by embodiments of the present application;

[0059] Figure 3 is a flow schematic diagram of another store situation determination method disclosed by embodiments of the present application;

[0060] Figure 4 is a schematic diagram between input and output of a probability model disclosed by embodiments of the present application;

[0061] Figure 5 is a flow schematic diagram of yet another store situation determination method disclosed by embodiments of the present application;

[0062] Figure 6 is a flow schematic diagram of yet another store situation determination method disclosed by embodiments of the present application;

[0063] Figure 7 is a schematic diagram of an application scenario of a store situation disclosed by embodiments of the present application;

[0064] Figure 8 is a schematic diagram of another application scenario of a store situation disclosed by embodiments of the present application;

[0065] Figure 9 is a schematic diagram of yet another application scenario of a store situation disclosed by embodiments of the present application;

[0066] Figure 10 is a structural schematic diagram of a store situation determination apparatus disclosed by embodiments of the present application;

[0067] Figure 11 is a structural schematic diagram of a computer device disclosed by embodiments of the present application. DETAILED DESCRIPTION

[0068] Example implementations will now be described more fully with reference to the accompanying drawings. Example implementations may, however, be implemented in many different forms and should not be construed as limited to the implementations set forth herein; rather, these implementations are provided so that this disclosure will be thorough and complete, and will fully convey the scope of example implementations to those skilled in the art.

[0069] Moreover, the described features, structures, or characteristics can be combined in any suitable manner in one or more embodiments. In the following description, numerous specific details are provided to give a thorough understanding of embodiments of the application. One skilled in the relevant art will recognize, however, that the application can be practiced without one or more of the specific details, or with other methods, components, materials, and so forth. In other instances, well-known structures, devices, implementations, or operations are not shown or described in detail to avoid obscuring aspects of the application.

[0070] The block diagrams in the drawings show only the functionality of the features and can not imply that the functions must be implemented in the particular order presented or that the functions must be implemented by the illustrated components. In some embodiments, the functionality of the features can be implemented in software, hardware, or a combination thereof.

[0071] The flow diagrams shown in the various figures are examples only and are not necessarily implemented in the order as shown. Some operations can be combined, some operations can be performed in a different order, and some operations can be performed in parallel. Also, some operations can be omitted, some operations can be performed by different components, and some operations can be performed by the same component.

[0072] It should be noted that the term "a plurality of" means two or more. The term "and / or" describes associated objects and can mean three cases: single case, joint case, and separate case. The character " / " generally means an "or" relationship between the front and rear associated objects.

[0073] In order to better understand the embodiments of the application, the related technologies of the application will be introduced first.

[0074] In order to improve the efficiency of physical stores, many store owners of physical stores will choose to attract users in the form of information push. In order to improve the accuracy and flexibility of information push, the push information of the user can be determined according to the store visit rate of the user. Therefore, optimizing the store visit rate of the user is a very urgent demand of the store owner, and the store visit data of the user is needed to optimize the store visit rate of the user.

[0075] Most physical stores will set up WIFI networks for users to connect and use. The store visit of the user can be predicted according to the WIFI connection of the user. Although the accuracy of judging the user's store visit based on WIFI connection is high, not all users will connect to the WIFI network after visiting the store, so the coverage is low.

[0076] In a case that the electronic device opens the WIFI, the electronic device will detect the WIFI network around. Therefore, in order to solve the above problem, the user's store visiting situation can be predicted based on the WIFI identifier of WIFI detection. However, the WIFI identifier of the store can be detected by the user within a certain range of the store, and therefore, the WIFI identifier of WIFI detection is directly used to determine the store visiting situation of the user, and the accuracy is low.

[0077] In order to solve the above problem, the application discloses a store visiting situation determination method, obtains the detection record of the first electronic device including M WIFI identifiers and M WIFI signal strengths, and the M WIFI identifiers and the M WIFI signal strengths are one-to-one corresponding; determine the WIFI feature according to the M WIFI identifiers, the M WIFI signal strengths, the first WIFI identifier and the WIFI identifier list, the first WIFI identifier is the WIFI identifier of the target store, the WIFI identifier list is the list of WIFI identifiers detected in the target store, and the WIFI identifier list includes the first WIFI identifier; determine the probability that the first object corresponding to the first electronic device has visited the target store according to the WIFI feature using the target probability model; and determine the situation that the first object has visited the target store according to the probability that the first object has visited the target store. In a case that the WIFI of the electronic device is opened, the electronic device will automatically detect the WIFI network around, the position of the electronic device is different, and the detected WIFI identifier and the corresponding WIFI signal strength can be different, and therefore, the user's store visiting situation can be determined according to the detected WIFI identifier and the corresponding WIFI signal strength, and the accuracy of the store visiting situation can be improved.

[0078] In order to better understand the embodiments of the application, the network architecture of the application will be introduced first.

[0079] Please refer to Figure 1 , Figure 1 is a structural schematic diagram of a network architecture disclosed by the embodiments of the application. As Figure 1 shown, the network architecture can include a plurality of WIFI devices 101, one or more electronic devices 102 and a computer device 103. The WIFI device 101 and the electronic device 102 can be connected through the WIFI network. The electronic device 102 and the computer device 103 can be connected through the network. The network can be a wide area network, a local area network or a combination of the two.

[0080] The WIFI device 101 can provide a WIFI network. The electronic device 102 is provided with a WIFI communication module. When the electronic device 102 is turned on WIFI, i.e., the function corresponding to the WIFI communication module on the electronic device is turned on, the electronic device 102 can detect the WIFI network provided by the WIFI device 101 within a certain range through the WIFI communication module, can obtain the identification (i.e., WIFI identification) of the detected WIFI device 101 (or the WIFI network provided by the WIFI device 101) and the WIFI signal strength of the WIFI network provided by the WIFI device, and can generate a detection record according to the detected WIFI identification and the corresponding WIFI signal strength.

[0081] In some embodiments, after the electronic device 102 generates the detection record, the electronic device 102 can actively send the detection record to the computer device 103.

[0082] In some embodiments, the computer device 103 can first send a request for obtaining the detection record to the electronic device 102. After receiving the request for obtaining from the computer device 103, the electronic device 102 can send the detection record to the computer device 103 according to the request for obtaining. The computer device 103 can receive the detection record from the electronic device 102.

[0083] The request for obtaining can include time information.

[0084] In one case, the time information is information of a certain time point. The electronic device 102 can send the detection record of this time point or the time point closest to the time interval with this time point to the computer device 103. The computer device 103 can receive the detection record of the electronic device 102 at this time point.

[0085] In another case, the time information is information of a certain time period. The electronic device 102 can send all the detection records generated in this time period to the computer device 103. After receiving all the detection records in this time period, the computer device 103 can generate the detection record of the electronic device in this time period according to these detection records. The detection record of the electronic device in this time period can include all the WIFI identifications in these detection records and the maximum WIFI signal strength corresponding to these WIFI identifications.

[0086] For example, the computer device 103 receives the detection record of 10:00-12:00 from the electronic device 102, which includes detection record 1 and detection record 2. The detection record 1 can be as shown in Table 1. The detection record 2 can be as shown in Table 2.

[0087] WIFI identity WIFI signal strength WIFI1 B1 WIFI2 B2 WIFI4 B3

[0088] Table 1

[0089] WIFI identity WIFI signal strength WIFI3 B4 WIFI4 B5 WIFI5 B6

[0090] Table 2

[0091] Suppose that B3 is greater than B5, the detection record of the electronic device 102 from 10:00 to 12:00 can be as shown in Table 3.

[0092] WIFI identity WIFI signal strength WIFI1 B1 WIFI2 B2 WIFI3 B4 WIFI4 B3 WIFI5 B6

[0093] Table 3

[0094] Afterwards, the computer device 103 can determine, according to the detection record of the electronic device 102, that the corresponding user has visited the target store, can determine, according to the user having visited the target store, a store visiting rate of the user having visited the target store, and can push information to the electronic device 102 according to the store visiting rate of the user having visited the target store.

[0095] The WIFI device can be various devices capable of providing a WIFI network, such as a WIFI router and the like.

[0096] The electronic device can be a device provided with a WIFI communication module and convenient to carry, such as a mobile phone, a telephone watch and the like.

[0097] In some embodiments, the computer device can implement the store visiting condition determination method provided in the embodiments of the present application by running a computer program. For example, the computer program can be a native program or a software module in an operating system; can be a native application program (APP), that is, a program that needs to be installed in an operating system to run; can also be a small program, that is, a program that only needs to be downloaded into a browser environment to run; and can also be a small program that can be embedded into any APP, wherein the small program can be controlled by a user to run or be turned off. In summary, the above computer program can be any form of application program, module or plug-in.

[0098] In some embodiments, the computer device can be a server or a terminal device. The server can be a stand-alone physical server, or a server cluster or distributed system composed of multiple physical servers, or a cloud server providing cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, content distribution networks (CDN), and basic cloud computing services such as big data and artificial intelligence platforms.

[0099] It should be understood that Figure 1 The above is an exemplary description of the network architecture of the present application, and does not limit the network architecture of the present application.

[0100] The implementation details of the technical solutions of the embodiments of the present application are described in detail as follows:

[0101] Based on the above network architecture, please refer to Figure 2 , Figure 2 is a flowchart of a store situation determination method disclosed by an embodiment of the present application. The store situation determination method can be applied to the computer device described above. As shown in Figure 2 , the store situation determination method can include the following steps.

[0102] 201, obtaining a probe record of a first electronic device including M WIFI identifiers and M WIFI signal strengths.

[0103] When it is needed to determine the situation of the first object to the target store, the probe record of the first electronic device can be obtained. The probe record of the first electronic device is the WIFI probe record of the first electronic device, i.e. the record generated by the first electronic device when it probes the WIFI network. The first object is the object corresponding to the first electronic device, i.e. the holder of the first electronic device.

[0104] The probe record of the first electronic device can include M WIFI identifiers and M WIFI signal strengths, which are one-to-one corresponding. That is, the probe record of the first electronic device includes M WIFI identifiers and the WIFI signal strength corresponding to each WIFI identifier in the M WIFI identifiers. M is an integer greater than 0.

[0105] The probe record of the first electronic device can be the probe record of the first electronic device at the first time, i.e. the probe record of the first electronic device at a certain time point. Correspondingly, the M WIFI identifiers and the M WIFI signal strengths can be the WIFI identifiers and the corresponding WIFI signal strengths of all WIFI networks detected by the first electronic device at the first time. The first time can be any time before the current time.

[0106] The probe record of the first electronic device can also be the probe record of the first electronic device at the first time period, i.e. the probe record of the first electronic device at a certain time period. Correspondingly, the M WIFI identifiers and the M WIFI signal strengths can be the WIFI identifiers and the corresponding WIFI signal strengths of all WIFI networks detected by the first electronic device at the first time period. The first time period can be any time period before the current time. The length of the first time period can be 1 hour, 1 day, 1 week, or other lengths.

[0107] In a case where the probe record of the first electronic device is a probe record of the first electronic device in the first time period, each of the M WIFI signal strengths is a maximum WIFI signal strength of a WIFI network corresponding to the first time period.

[0108] The WIFI identifier is an identifier of the WIFI network, and is used to identify the WIFI network. The WIFI identifier can be a name of the WIFI network, or can be other information capable of uniquely identifying the WIFI network.

[0109] The WIFI signal strength is a strength of a WIFI signal of the WIFI network. The WIFI signal strength detected by the electronic device is inversely proportional to a distance between the electronic device and the WIFI device, that is, the smaller the distance between the electronic device and the WIFI device, the stronger the WIFI signal strength of the WIFI network provided by the WIFI device detected by the electronic device.

[0110] In the specific embodiments of the present application, related data such as probe records and tags are involved. When the embodiments in the present application are applied to specific products or technologies, the collection, use and processing of related data (such as probe records) need to comply with relevant laws, regulations and standards of relevant countries and regions.

[0111] 202. Determine a WIFI feature according to the M WIFI identifiers, the M WIFI signal strengths, the first WIFI identifier and a WIFI identifier list.

[0112] The first WIFI identifier is a WIFI identifier of a target store. The target store is any store in a physical store. The first WIFI identifier can include one WIFI identifier, or can include multiple WIFI identifiers.

[0113] In a case where the target store is provided with one WIFI network, the first WIFI identifier includes one WIFI identifier, that is, an identifier of the WIFI network.

[0114] In a case where the target store is provided with multiple WIFI networks, the first WIFI identifier includes multiple WIFI identifiers, that is, identifiers of the multiple WIFI networks.

[0115] The WIFI identifier list is a list of WIFI identifiers detected in the target store, that is, a list of identifiers of all WIFI networks that can be detected by the electronic device in the target store. The WIFI identifier list includes the first WIFI identifier, that is, the WIFI identifier list includes an identifier of a WIFI network of the target store itself.

[0116] For example, when the WIFI of the electronic device is turned on, the electronic device detects 10 WIFI networks in store 1, and the WIFI identification list includes the identifications of these 10 WIFI networks.

[0117] The list of identifiers of all WIFI networks that the electronic device can detect in the target store can be understood as a list of identifiers of all WIFI networks that the electronic device can detect at any location in the target store.

[0118] For example, when the WIFI of the electronic device is turned on, the electronic device detects WIFI1 and WIFI2 at location 1 in store 1, and detects WIFI1 and WIFI3 at location 2 in store 1, and the WIFI identification list includes WIFI1, WIFI2 and WIFI3.

[0119] After obtaining the detection record of the first electronic device, the WIFI feature can be determined based on the M WIFI identifiers, the M WIFI signal strengths, the first WIFI identifier and the WIFI identifier list, that is, the WIFI feature can be determined based on the detection record of the first electronic device, the first WIFI identifier and the WIFI identifier list.

[0120] In some embodiments, the WIFI signal strength includes K strength levels, where K is an integer greater than 1. After obtaining the detection record of the first electronic device, the WIFI identifiers belonging to the WIFI identifier list among the M WIFI identifiers can be determined to obtain N WIFI identifiers. The detection characteristics can be determined based on the detection probabilities corresponding to the N WIFI identifiers. The strength level corresponding to each WIFI signal strength among the N WIFI signal strengths can be determined based on the K strength levels to obtain the current strength level corresponding to the N WIFI identifiers. The strength characteristics can be determined based on the strength probabilities corresponding to the current strength levels of the N WIFI identifiers and the first WIFI identifier. N is an integer less than or equal to M. The N WIFI signal strengths are the WIFI signal strengths corresponding to the N WIFI identifiers among the M WIFI signal strengths.

[0121] Different Wi-Fi signal strengths indicate different distances between the electronic device and the Wi-Fi device. To accurately determine the user's presence at the store, the Wi-Fi signal strength can be divided into K strength levels. Therefore, the Wi-Fi signal strength can include K strength levels, with different strength levels corresponding to different Wi-Fi signal strength ranges. K is an integer greater than 1.

[0122] The corresponding relationship between the WIFI signal strength interval and the strength level can be shown in Table 4:

[0123] WIFI signal strength Strength level [0，A1) Level 1 [A1, A2) Level 2 … … [AK, +∞) Level K

[0124] Table 4

[0125] wherein values of A1, A2, …, AK are sequentially increased, and are all values greater than 0.

[0126] The detection probability corresponding to each WIFI identifier in the WIFI identifier list and the strength probability corresponding to each strength level in the K strength levels corresponding to each WIFI identifier in the WIFI identifier list can be pre-calculated according to historical detection records and historical user store visit situations. The historical detection records are detection records before the current time, and the historical user store visit situations are user visit situations to the target store corresponding to the historical detection records.

[0127] The detection probability corresponding to a WIFI identifier is the probability that the electronic device detects the WIFI network indicated by the WIFI identifier under the condition that the object (i.e., the user) visits the target store. The detection probability corresponding to the i-th WIFI identifier in the WIFI identifier list can be expressed as follows:

[0128]

[0129] wherein P(WIFI i |SHOP) represents the detection probability corresponding to the i-th WIFI identifier in the WIFI identifier list by the electronic device of the object under the condition that the object visits the target store SHOP, P(SHOP) represents the probability that the object visits the target store, and P(WIFI i |SHOP) represents the probability that the object visits the target store SHOP and the electronic device of the object detects the i-th WIFI identifier in the WIFI identifier list. The detection probability corresponding to the WIFI identifier list, i.e., the detection probability list, can be as shown in Table 5:

[0130] WIFI identity Probe probability WIFI1 P1 WIFI2 P2 … …

[0131] Table 5 Detection probability list

[0132] The detection probabilities P1, P2, …, etc., are numbers greater than 0 and less than or equal to 1.

[0133] The strength probability corresponding to the j-th strength level corresponding to a WIFI identifier is the probability that the strength level corresponding to the WIFI signal strength of the WIFI network indicated by the WIFI identifier detected by the electronic device is the j-th strength level under the condition that the object visits the target store. The strength probability corresponding to the j-th strength level corresponding to the i-th WIFI identifier in the WIFI identifier list can be expressed as follows:

[0134]

[0135] wherein RSSIS ijP(RSSIS, j) represents the probability that the i-th WIFI identifier in the WIFI identifier list corresponds to the j-th intensity level. ij P(RSSIS, j | SHOP) represents the probability that the i-th WIFI identifier in the WIFI identifier list corresponds to the j-th intensity level in the case that the object enters the target store SHOP. ij P(RSSIS, j | SHOP) represents the probability that the i-th WIFI identifier in the WIFI identifier list corresponds to the j-th intensity level in the case that the object enters the target store SHOP.

[0136] The intensity probabilities of the WIFI identifier list corresponding to the K intensity levels, i.e., the intensity probability list, can be as shown in Table 6:

[0137]

[0138] Table 6 Intensity probability list

[0139] The intensity probabilities P11, P12, …, P21, P22, … are numbers greater than or equal to 0 and less than or equal to 1.

[0140] The N WIFI identifiers can be determined from the M WIFI identifiers that belong to the WIFI identifier list, i.e., the WIFI identifiers belonging to the WIFI identifier list are selected from the M WIFI identifiers. The intersection of the M WIFI identifiers and the WIFI identifier list can be determined to obtain the N WIFI identifiers.

[0141] The detection probability list can be obtained, and the detection probability corresponding to each WIFI identifier in the N WIFI identifiers can be determined according to the detection probability list to obtain the detection probability corresponding to the N WIFI identifiers. The detection feature can be determined according to the detection probability corresponding to the N WIFI identifiers.

[0142] As can be known from Table 4 and the related description, the correspondence between different WIFI signal intensity intervals and the K intensity levels has been determined in advance. The correspondence between the WIFI signal intensity interval and the intensity level can be obtained. The target WIFI signal intensity interval corresponding to each WIFI signal intensity in the N WIFI signal intensities can be determined to obtain the N target WIFI signal intensity intervals. According to the correspondence, the intensity level corresponding to each target WIFI signal intensity interval in the N target WIFI signal intensity intervals can be determined to obtain the current intensity level corresponding to the N WIFI identifiers, i.e., the current level corresponding to the WIFI signal intensity corresponding to each WIFI identifier in the N WIFI identifiers.

[0143] For example, assuming that the WIFI signal strength corresponding to WIFI identifier 1 is a1, a1 is greater than A1 and less than A2, then the WIFI signal strength interval corresponding to a1 is [A1, A2), according to the corresponding relationship between the WIFI signal strength interval and the strength level, level 2 corresponding to [A1, A2) is determined as the current level corresponding to WIFI identifier 1.

[0144] It can be seen that the current strength level corresponding to the N WIFI identifiers is one of the K strength levels.

[0145] The strength probability list can be obtained, the strength probability corresponding to the current strength level of the N WIFI identifiers can be determined according to the strength probability list, and then the strength feature can be determined according to the strength probability corresponding to the strength level of the N WIFI identifiers and the first WIFI identifier.

[0146] Since the required detection probability and strength probability are pre-statistics, the determination efficiency of the detection feature and the strength feature can be improved, and then the determination efficiency of the user store condition can be improved. In addition, since the detection probability and the strength probability are obtained according to the historical detection record and the historical user store condition, the data is real and reliable, so the detection probability and the strength probability have high accuracy, thereby the accuracy of the user store condition can be improved. Further, when determining the detection probability and the strength probability, not only the WIFI identifier and the corresponding WIFI signal strength of the target store are considered, but also other WIFI identifiers and corresponding WIFI signal strengths that can be detected in the target store are considered. The other WIFI identifiers and the corresponding WIFI signal strengths can verify the WIFI identifier and the corresponding WIFI signal strength of the target store, and the accuracy of the user store condition can be improved.

[0147] In some embodiments, the sum of the detection probabilities corresponding to the N WIFI identifiers can be determined to obtain a first feature, the average of the detection probabilities corresponding to the N WIFI identifiers can be determined to obtain a second feature, and the maximum value of the detection probabilities corresponding to the N WIFI identifiers can be determined to obtain a third feature. Then, the detection feature can be determined according to at least one of the first feature, the second feature and the third feature.

[0148] In order to weaken the assumption that different WIFI networks are independent of each other, the sum, the average and the maximum value of the detection probabilities corresponding to the N WIFI identifiers can be determined, and the first feature, the second feature and the third feature can be represented as follows:

[0149]

[0150]

[0151]

[0152] wherein MAX denotes taking the maximum value and AVG denotes taking the average value.

[0153] In the case where N is 0, the first feature, the second feature and the third feature are all 0.

[0154] The detection feature can include the first feature, the second feature or the third feature, can include any two of the first feature, the second feature and the third feature, or can include the first feature, the second feature and the third feature.

[0155] In some embodiments, a fourth feature can be determined by summing the strength probabilities corresponding to the current strength level for the N WIFI identifiers, a fifth feature can be determined by averaging the strength probabilities corresponding to the current strength level for the N WIFI identifiers, a sixth feature can be determined by taking the maximum value of the strength probabilities corresponding to the current strength level for the N WIFI identifiers, and a seventh feature can be determined by determining the WIFI signal strength of the target store according to the N WIFI signal strengths and the first WIFI identifier. Then, the strength feature can be determined according to at least one of the fourth feature, the fifth feature and the sixth feature, and the seventh feature.

[0156] Similarly, in order to weaken the assumption that different WIFI networks are independent of each other, the strength feature can be determined by summing, averaging and taking the maximum value of the strength probabilities corresponding to the strength levels for the N WIFI identifiers. The fourth feature, the fifth feature, the sixth feature and the seventh feature can be represented as follows:

[0157]

[0158]

[0159]

[0160] The seventh feature = the WIFI signal strength of the target store

[0161] In the case where the first WIFI identifier includes one WIFI identifier and the N WIFI identifiers include the first WIFI identifier, the WIFI signal strength corresponding to the first WIFI identifier in the N WIFI signal strengths can be determined as the WIFI signal strength of the target store. In the case where the first WIFI identifier includes one WIFI identifier and the N WIFI identifiers do not include the first WIFI identifier, the WIFI signal strength of the target store is determined as 0.

[0162] In a case that the first WIFI identifier includes multiple WIFI identifiers and the N WIFI identifiers include one WIFI identifier in the first WIFI identifiers, a WIFI signal strength corresponding to the one WIFI identifier in the N WIFI signal strengths can be determined as the WIFI signal strength of the target store. In a case that the first WIFI identifier includes multiple WIFI identifiers and the N WIFI identifiers include at least two WIFI identifiers in the first WIFI identifiers, a maximum WIFI signal strength in WIFI signal strengths corresponding to the at least two WIFI identifiers in the N WIFI signal strengths can be determined as the WIFI signal strength of the target store. In a case that the first WIFI identifier includes multiple WIFI identifiers and the N WIFI identifiers do not include any WIFI identifier in the first WIFI identifiers, the WIFI signal strength of the target store is determined as 0.

[0163] The strength feature can include the fourth feature, the fifth feature or the sixth feature, and the seventh feature; can also include any two of the fourth feature, the fifth feature and the sixth feature, and the seventh feature; and can further include the fourth feature, the fifth feature, the sixth feature and the seventh feature.

[0164] It can be seen that, when the feature is determined, the WIFI identifiers and the corresponding WIFI signal strengths in the detected WIFI identifier list are not taken as features respectively, but the features are determined jointly by the WIFI identifiers and the corresponding WIFI signal strengths, the independence between different WIFI networks can be weakened, the connection between the WIFI identifiers in the WIFI identifier list can be improved, and thus the accuracy of the user store visiting probability can be improved.

[0165] In a case that N is 0, the fourth feature, the fifth feature, the sixth feature and the seventh feature are all 0.

[0166] 203. Determine the probability that the first object has visited the target store according to the target probability model used for the WIFI feature.

[0167] The target probability model is a pre-trained probability model corresponding to the target store.

[0168] After the WIFI feature is determined, the probability that the first object has visited the target store can be determined according to the target probability model used for the WIFI feature, that is, the WIFI feature can be input into the target probability model, and the output of the target probability model is the probability that the first object has visited the target store.

[0169] In a case where the WIFI feature includes the detection feature and the strength feature, after the detection feature and the strength feature are determined, the probability model can be used to determine the probability that the first object has been to the target store according to the detection feature and the strength feature, that is, the detection feature and the strength feature can be input into the probability model, and the output of the probability model is the probability that the first object has been to the target store.

[0170] 204. Determine, according to the probability that the first object has been to the target store, the case that the first object has been to the target store.

[0171] After the probability that the first object has been to the target store is determined, the case that the first object has been to the target store can be determined according to the probability that the first object has been to the target store. The relationship between the probability that the first object has been to the target store and the case that the first object has been to the target store can be represented as follows:

[0172]

[0173] Wherein, label represents the case that the first object has been to the target store, and P1 represents the probability that the first object has been to the target store.

[0174] It can be seen that the probability that the first object has been to the target store can be compared with the probability threshold, and in a case where the probability that the first object has been to the target store is greater than or equal to the probability threshold, it can be determined that the first object has been to the target store. In a case where the probability that the first object has been to the target store is less than the probability threshold, it can be determined that the first object has not been to the target store.

[0175] In Figure 2 In the store case determination method described above, in a case where the WIFI of the electronic device is turned on, the electronic device will automatically detect the surrounding WIFI network. The position of the electronic device is different, and the detected WIFI identifier and the corresponding WIFI signal strength can be different. Therefore, the user's store case can be determined according to the detected WIFI identifier and the corresponding WIFI signal strength, which can improve the accuracy of the store case.

[0176] Based on the above network architecture, please refer to Figure 3 , Figure 3 is a flowchart of another store case determination method disclosed by the embodiments of the present application. Wherein, the store case determination method can be applied to the computer device described above. As Figure 3 shown, the store case determination method can include the following steps.

[0177] 301. Obtain training data including detection records of a plurality of electronic devices and labels of corresponding objects of the plurality of electronic devices having been to a target store.

[0178] In the case of training the probability model, training data can be acquired first. The training data can include the probe records of a plurality of electronic devices and labels of objects corresponding to the plurality of electronic devices to the target store. The probe records of different electronic devices can be the same or different.

[0179] The probe record of the second electronic device includes M WIFI identifiers and M WIFI signal strengths, which are one-to-one corresponding. For detailed description, reference can be made to the description of the probe record of the first electronic device in step 101. The second electronic device is any electronic device in the plurality of electronic devices.

[0180] In the case of the object corresponding to the second electronic device to the target store, the label of the object corresponding to the second electronic device to the target store is 1. In the case of the object corresponding to the second electronic device not to the target store, the label of the object corresponding to the second electronic device to the target store is 0.

[0181] The training data includes positive samples and negative samples. The label corresponding to the positive sample is 1, and the label corresponding to the negative sample is 0. In order to ensure the accuracy of the trained probability model, the number of samples included in the training data should be sufficient.

[0182] 302. Determine the probe feature and the intensity feature corresponding to the second electronic device according to the probe record of the second electronic device, the first WIFI identifier and the WIFI identifier list.

[0183] The way of determining the probe feature and the intensity feature corresponding to the second electronic device is the same as the way of determining the probe feature and the intensity feature corresponding to the first electronic device. For detailed description of step 302, reference can be made to step 202.

[0184] 303. Determine the predicted probability of the second object to the target store using the initial probability model according to the probe feature and the intensity feature corresponding to the second electronic device.

[0185] The second object is the object corresponding to the second electronic device, i.e. the holder of the second electronic device.

[0186] For detailed description of step 303, reference can be made to step 203.

[0187] 304. Determine the loss value according to the predicted probability of the second object to the target store and the label.

[0188] After determining the predicted probability of the second object to the target store, the loss value can be determined according to the predicted probability of the second object to the target store and the label.

[0189] The type of the loss function used to calculate the loss value is not limited. For example, the loss function can be a cross-entropy loss function, an L1 (i.e., absolute error) loss function, an L2 (i.e., mean squared error) loss function, a smooth loss function, etc.

[0190] 305. Optimizing the parameters of the initial probability model according to the loss value to obtain a target probability model.

[0191] After the loss value is determined, the parameters of the initial probability model can be optimized according to the loss value to obtain a target probability model. For example, the parameters of the initial probability model can be optimized by a back propagation (BP) algorithm.

[0192] The above-mentioned first determining the predicted probability that the user has visited the target store, and then determining the loss value according to the predicted probability that the user has visited the target store and the label, and updating the parameters of the initial probability model according to the loss value, can realize effective updating of the parameters of the initial probability model, that is, can improve the training effect.

[0193] The relationship between the input and the output of the probability model can be expressed as follows:

[0194]

[0195] where f(x) represents the output of the probability model, and x represents the input of the probability model.

[0196] For example, x = [first feature, second feature, third feature, fourth feature, fifth feature, sixth feature, seventh feature]. As can be seen, the input of the probability model is a column matrix composed of seven features, and w is a row matrix including seven values.

[0197] Training the initial probability model is to determine w.

[0198] Please refer to Figure 4 , Figure 4 is a schematic diagram of the input and the output of a probability model disclosed in an embodiment of the present application. As shown in Figure 4 , f(x) is greater than or equal to 0 and less than or equal to 1.

[0199] After the target probability model is obtained, the target probability model can be verified according to the verification data. If the accuracy of the target probability model is greater than or equal to a first threshold value and the recall rate is greater than or equal to a second threshold value, it can be determined that the target probability model is successfully trained; if the accuracy of the target probability model is less than the first threshold value or the recall rate is less than the second threshold value, the training data can be reacquired to continue training the target probability model until the accuracy is greater than or equal to the first threshold value and the recall rate is greater than or equal to the second threshold value.

[0200] For example, assuming that the accuracy is 85% and the recall is 80%, when it is verified that the accuracy of the target probability model is 88% and the recall is greater than 85%, it can be determined that the training of the target probability model is successful.

[0201] 306. Obtain a detection record of the first electronic device including M WIFI identifiers and M WIFI signal strengths.

[0202] The detailed description of step 306 can refer to step 201 and will not be repeated here.

[0203] 307. Determine a WIFI feature according to the M WIFI identifiers, the M WIFI signal strengths, the first WIFI identifier, and the WIFI identifier list.

[0204] The detailed description of step 307 can refer to step 202 and will not be repeated here.

[0205] 308. Determine the probability that the first subject has visited the target store using a target probability model based on the Wi-Fi feature.

[0206] The detailed description of step 308 can refer to step 203 and will not be repeated here.

[0207] 309. Determine whether the first subject has visited the target store based on the probability that the first subject has visited the target store.

[0208] The detailed description of step 309 can refer to step 204 and will not be repeated here.

[0209] exist Figure 3 In the described method for determining store visit status, a target probability model is first trained using training data. The trained target probability model is then used to predict the probability of a user visiting a target store, thereby determining whether the user has visited the target store. This eliminates the need for training the probability model each time it is used, improving the efficiency of determining store visit status. When Wi-Fi is turned on on an electronic device, the device automatically detects surrounding Wi-Fi networks. The detected Wi-Fi identifier and corresponding Wi-Fi signal strength may vary depending on the location of the electronic device. Therefore, training the probability model based on the detected Wi-Fi identifier and corresponding Wi-Fi signal strength can improve the accuracy of the target probability model, and thus the accuracy of store visit status.

[0210] Based on the above network architecture, please refer to Figure 5 , Figure 5 This is a flow chart of another method for determining store arrival status disclosed in an embodiment of the present application. The method for determining store arrival status can be applied to the above-mentioned computer device. Figure 5As shown, the method for determining store arrival status may include the following steps.

[0211] 501. Obtain training data including detection records of multiple electronic devices and labels indicating that the multiple electronic devices correspond to objects that have visited a target store.

[0212] For a detailed description of step 501 , please refer to the relevant description below step 301 .

[0213] 502. Determine the total number of times the subject has visited the store based on the tags of multiple electronic devices.

[0214] When the probability of a user visiting a target store is determined based on the detected Wi-Fi identifier and the Wi-Fi signal strength corresponding to the Wi-Fi identifier, the probability of the user visiting the target store can be expressed as P(SHOP|WIFI, RSSIS). P(SHOP|WIFI, RSSIS) is the probability of the user visiting the target store given the detected Wi-Fi identifier and the Wi-Fi signal strength corresponding to the Wi-Fi identifier. Based on the Bayesian theorem and the independence assumption, P(SHOP|WIFI, RSSIS) can be expressed as follows:

[0215]

[0216] P(SHOP) / P(WIFI, RSSIS) in the above formula can be regarded as a constant. According to the above formula, the focus of determining the probability that the user has visited the target store lies in P(WIFI︱SHOP) and P(RSSIS︱SHOP). P(WIFI︱SHOP) is the distribution of WIFI identifiers detected by the user's electronic device when the user visits the target store. P(RSSIS︱SHOP) is the distribution of WIFI signal strength detected by the user's electronic device when the user visits the target store. The following uses P(WIFI︱SHOP) as an example. Assuming that different WIFI networks are independent of each other, P(WIFI︱SHOP) can be expressed as follows:

[0217]

[0218]

[0219] Where L is the number of WIFI identifiers included in the WIFI identifier list. According to the law of large numbers, P(WIFI i ︱SHOP) can be expressed as follows:

[0220]

[0221] The number of times that the object goes to the target store and detects the i-th WIFI identifier can be understood as the number of times that the object goes to the target store SHOP and the electronic device of the object detects the i-th WIFI identifier in the WIFI identifier list.

[0222] Similarly, P(RSSIS ij The P(RSSIS

[0223]

[0224] The number of times that the object goes to the target store and detects the i-th WIFI identifier corresponding to the j-th intensity level can be understood as the number of times that the object goes to the target store SHOP and the electronic device of the object detects the i-th WIFI identifier in the WIFI identifier list corresponding to the WIFI signal strength corresponding to the intensity level being the j-th intensity level.

[0225] After obtaining the training data, the total number of times that the object goes to the store can be determined according to the labels corresponding to the plurality of electronic devices, that is, the total number of times that the object (that is, the user) goes to the target store, that is, the number of labels corresponding to the plurality of electronic devices that go to the target store is counted. The label corresponding to the electronic device, that is, the label corresponding to the object going to the target store.

[0226] 503, according to the detection record of the plurality of electronic devices and the label of the plurality of electronic devices, the number of times that the object goes to the target store and detects the second WIFI identifier is obtained.

[0227] After obtaining the training data, the electronic device with a label of 1 can be selected from the plurality of electronic devices to obtain T electronic devices, and then the number of electronic devices in the T electronic devices whose detection records include the second WIFI identifier can be counted to obtain the number of times that the object goes to the target store and detects the second WIFI identifier, that is, the number of times that the object goes to the target store and detects the second WIFI identifier, that is, the first number. T is an integer greater than 1.

[0228] 504, according to the detection record of the plurality of electronic devices and the label of the plurality of electronic devices, the number of times that the object goes to the target store and detects the second WIFI identifier corresponding to the target intensity level is obtained.

[0229] After the training data is obtained, the electronic devices with the label of 1 can be selected from the plurality of electronic devices to obtain T electronic devices. The electronic devices whose detection records include the second WIFI identifier can be selected from the T electronic devices to obtain U electronic devices. The strength levels of the WIFI signal strengths corresponding to the second WIFI identifiers detected by the U electronic devices are determined. Then, the number of electronic devices whose detection records include the second WIFI identifier and whose strength levels are the target strength level can be counted to obtain the number of times that the object goes to the store and detects the second WIFI identifier corresponding to the target strength level, i.e., the first number of times.

[0230] Steps 502-504 can be executed in parallel or in series.

[0231] 505. Determine the detection probability corresponding to the second WIFI identifier according to the first number of times and the total number of times that the object goes to the store.

[0232] The ratio of the first number of times to the total number of times that the object goes to the store can be determined as the detection probability corresponding to the second WIFI identifier.

[0233] 506. Determine the strength probability corresponding to the target strength level of the second WIFI identifier according to the second number of times and the total number of times that the object goes to the store.

[0234] The ratio of the second number of times to the total number of times that the object goes to the store can be determined as the strength probability corresponding to the target strength level of the second WIFI identifier.

[0235] As can be seen, the detection probability and the strength probability determined in the above manner are obtained by a large amount of data statistics, which can improve the accuracy of the detection probability and the strength probability.

[0236] Steps 505-506 can be executed in parallel or in series.

[0237] Steps 502-506 determine the detection probability and the strength probability according to the training data.

[0238] It should be understood that other data can also be used to determine the detection probability and the strength probability. For example, before the initial probability model is trained, i.e., before step 501, statistical data can be obtained first. Then, the detection probability and the strength probability can be determined according to the statistical data. The statistical data can include the detection records of the plurality of electronic devices and the labels of the objects going to the target store corresponding to the plurality of electronic devices.

[0239] The statistical data is different from the training data. The statistical data can be different from the training data in whole or in part.

[0240] 507、determine the probe feature and the intensity feature corresponding to the second electronic device according to the probe record of the second electronic device, the first WIFI identifier and the WIFI identifier list.

[0241] The detailed description of step 507 can refer to step 202.

[0242] 508、determine the predicted probability of the second object passing the target store according to the probe feature and the intensity feature corresponding to the second electronic device using the initial probability model.

[0243] The detailed description of step 508 can refer to step 203.

[0244] 509、determine the loss value according to the predicted probability of the second object passing the target store and the label.

[0245] The detailed description of step 509 can refer to step 304.

[0246] 510、optimize the parameters of the initial probability model to obtain a target probability model according to the loss value.

[0247] The detailed description of step 510 can refer to step 305.

[0248] 511、obtain the probe record of the first electronic device.

[0249] The detailed description of step 511 can refer to step 201, which will not be repeated here.

[0250] 512、determine the WIFI feature according to the M WIFI identifiers, the M WIFI signal strengths, the first WIFI identifier and the WIFI identifier list.

[0251] The detailed description of step 512 can refer to step 202, which will not be repeated here.

[0252] 513、determine the probability of the first object passing the target store according to the WIFI feature using the target probability model.

[0253] The detailed description of step 513 can refer to step 203, which will not be repeated here.

[0254] 514、determine the situation of the first object passing the target store according to the probability of the first object passing the target store.

[0255] The detailed description of step 514 can refer to step 204, which will not be repeated here.

[0256] In Figure 5In the described store visit situation determination method, the detection probability and the intensity probability are determined through the training data, then the target probability model is trained according to the training data, the trained target probability model is used to predict the probability of the user visiting the target store, and then the situation of the user visiting the target store is determined, without the need to determine the detection probability and the intensity probability every time the probability model is used, and the probability model is trained, which can improve the determination efficiency of the store visit situation. When the WIFI of the electronic device is turned on, the electronic device will automatically detect the surrounding WIFI network. The position of the electronic device is different, and the detected WIFI identifier and the corresponding WIFI signal strength may be different. Therefore, the probability model is trained according to the detected WIFI identifier and the corresponding WIFI signal strength, which can improve the accuracy of the target probability model, and then the accuracy of the store visit situation can be improved.

[0257] Based on the above network architecture, please refer to Figure 6 , Figure 6 is a flowchart of another store visit situation determination method disclosed in the embodiments of the present application. The store visit situation determination method can be applied to the above computer device. As shown in Figure 6 , the store visit situation determination method can include the following steps.

[0258] 601, obtaining the detection record of the first electronic device.

[0259] The detailed description of step 601 can be referred to step 201, which will not be repeated here.

[0260] 602, determining the WIFI feature according to the M WIFI identifiers, the M WIFI signal strengths, the first WIFI identifier and the WIFI identifier list.

[0261] The detailed description of step 602 can be referred to step 202, which will not be repeated here.

[0262] 603, determining the probability of the first object visiting the target store according to the WIFI feature using the target probability model.

[0263] The detailed description of step 603 can be referred to step 203, which will not be repeated here.

[0264] 604, determining the situation of the first object visiting the target store according to the probability of the first object visiting the target store.

[0265] The detailed description of step 604 can be referred to step 204, which will not be repeated here.

[0266] 605, determining the store visit rate of the first object to the target store according to the situation of the first object visiting the target store.

[0267] After determining the situation of the first object going to the target store, the store-visit rate of the first object to the target store can be determined according to the situation of the first object going to the target store.

[0268] The store-visit rate of the first object to the target store can be determined as the ratio of the number of times the first object goes to the target store to the number of times the first object makes an appointment with the target store, or as the ratio of the number of times the first object goes to the target store to the number of times the information is pushed. The number of times the information is pushed refers to the number of times the information corresponding to the target store is sent to the first electronic device. The information corresponding to the target store can be service information of the target store, activity information of the target store, or other information of the target store.

[0269] 606. Determine the target information according to the store-visit rate of the first object to the target store.

[0270] After determining the store-visit rate of the first object to the target store, the target information can be determined according to the store-visit rate of the first object to the target store. The target information is information corresponding to the target store that needs to be sent to the first electronic device.

[0271] In one case, the store-visit rate is different, and the information to be pushed is different. Therefore, after determining the store-visit rate of the first object to the target store, the information corresponding to the store-visit rate of the first object to the target store can be determined according to the correspondence between the store-visit rate and the information, and the target information is obtained.

[0272] In another case, the store-visit rate interval is different, and the information to be pushed is different. Therefore, after determining the store-visit rate of the first object to the target store, the target store-visit rate interval corresponding to the store-visit rate of the first object to the target store can be determined, and then the information corresponding to the target store-visit rate interval can be determined according to the correspondence between the store-visit rate interval and the information, and the target information is obtained.

[0273] 607. Send the target information to the first electronic device.

[0274] After determining the information to be pushed, the information to be pushed can be sent to the first electronic device to push the information to the first object.

[0275] In Figure 6The described store situation determination method first determines the store situation of a user, then determines the store rate corresponding to the user according to the store situation of the user, and then can push information to the user according to the store rate corresponding to the user, which can avoid pushing fixed information to the user and improve the accuracy and flexibility of information pushing. In addition, when the WIFI of the electronic device is turned on, the electronic device will automatically detect the WIFI network around it. The position of the electronic device is different, and the detected WIFI identifier and the corresponding WIFI signal strength may be different. Therefore, the store situation of the user is determined according to the detected WIFI identifier and the corresponding WIFI signal strength, which can improve the accuracy of the store situation.

[0276] In some embodiments, after determining the store situation of the first object to the target store, the store rate of the target store can also be determined according to the store situation of the first object to the target store.

[0277] The ratio of the total number of objects to the target store to the total number of objects that reserve the target store can be determined as the store rate of the target store. The ratio of the total number of objects to the target store to the total number of objects that push information can also be determined as the store rate of the target store. The total number of objects that push information is the total number of objects that push information.

[0278] In order to better understand the embodiments of the present application, the following will be described in conjunction with application scenarios. The following application scenarios are described by taking advertisement placement as an example.

[0279] Please refer to Figure 7 , Figure 7 is a store situation application scenario disclosed by an embodiment of the present application. As shown in Figure 7 , the electronic device of the user can perform WIFI detection, can generate a detection record according to the result of WIFI detection, and then can send the generated detection record to the advertisement placement platform (i.e. the above-mentioned computer device). After receiving the detection record, the advertisement placement platform can determine the store situation of the user to the store according to the detection record using the above-mentioned method, can determine the store rate of the user to the store according to the store situation of the user to the store, and can determine the advertisement to be pushed according to the store rate of the user to the store. Then the advertisement to be pushed can be sent to the electronic device of the user to realize pushing the corresponding advertisement to the user according to the store rate of the user to the store, which can improve the adaptability and flexibility of advertisement placement.

[0280] Please refer to Figure 8 , Figure 8 is another store situation application scenario disclosed by an embodiment of the present application. As shown in Figure 8As shown in FIG. 6, the electronic device of the user can perform WIFI detection, can generate a detection record according to the result of the WIFI detection, and can then send the generated detection record to the advertisement launching platform. After receiving the detection record, the advertisement launching platform can determine, according to the detection record, whether the user has visited the store by using the method described above, can determine the store visit rate of the store according to the user's visit to the store, and can then send the store visit rate of the store to the electronic device of the store owner, so that the store owner can know the effect of the advertisement in time.

[0281] Please refer to Figure 9 , Figure 9 FIG. 7 is another application scenario of the store visit situation disclosed in the embodiments of the present application. As shown in FIG. 7, the electronic device of the user can perform WIFI detection, can generate a detection record according to the result of the WIFI detection, and can then send the generated detection record to the advertisement launching platform. After receiving the detection record, the advertisement launching platform can determine, according to the detection record, whether the user has visited the store by using the method described above, can determine the store visit rate of the store according to the user's visit to the store, and can then adjust the advertisement launching strategy according to the store visit rate of the store. Figure 9

[0282] In one case, the advertisement launching platform can periodically or regularly determine the store visit rate of the store, and can then adjust the advertisement launching strategy according to the store visit rate of the store. It can be seen that the advertisement launching strategy can be adjusted in time according to the effect of the advertisement launching, and the flexibility of the advertisement launching can be improved.

[0283] In another case, the advertisement launching platform can periodically or regularly determine the store visit rate of the store, and can then determine whether the store visit rate of the store is greater than or equal to an effect threshold. In the case where it is determined that the store visit rate of the store is greater than or equal to the effect threshold, it indicates that the effect of the current advertisement launching strategy is good, and the current advertisement launching strategy can be kept unchanged. In the case where it is determined that the store visit rate of the store is less than the effect threshold, it indicates that the effect of the current advertisement launching strategy is poor, and the advertisement launching strategy can be adjusted according to the store visit rate of the store. It can be seen that in the case where the effect of the advertisement launching is poor, the advertisement launching strategy can be adjusted according to the effect of the advertisement launching, and the effect of the advertisement launching can be improved.

[0284] In some embodiments, the advertisement launching platform can send the store visit rate of the store to the electronic device of the store owner, so that the store owner can know the effect of the advertisement in time.

[0285] In some embodiments, after the advertisement launching platform adjusts the advertisement launching strategy, the advertisement launching platform can send the adjusted advertisement launching strategy to the electronic device of the store owner, so that the store owner can know the current advertisement launching strategy in time.

[0286] ​In some embodiments, after the advertising platform determines the advertising strategy to be adjusted, the advertising platform can send an adjustment request to the electronic device of the store owner, the adjustment request including the advertising strategy to be adjusted. After the electronic device of the store owner receives the advertising strategy to be adjusted, the electronic device can output prompt information prompting the user whether to adjust the advertising strategy. The prompt information includes the advertising strategy to be adjusted.

[0287] In the case where the store owner needs to adjust the advertising strategy, the store owner can perform a confirmation operation on the prompt information. In response to the confirmation operation of the store owner on the prompt information, the electronic device of the store owner can send first indication information for modifying the advertising strategy to the advertising platform. After the advertising platform receives the first indication information, the advertising platform can adjust the advertising strategy to the advertising strategy to be adjusted according to the first indication information.

[0288] In the case where the store owner does not need to adjust the advertising strategy, the store owner can perform a denial operation on the prompt information. In response to the denial operation of the store owner on the prompt information, the electronic device of the store owner can send second indication information for not modifying the advertising strategy to the advertising platform. After the advertising platform receives the second indication information, the advertising platform can keep the advertising strategy unchanged.

[0289] As can be seen, the advertising platform can determine whether to modify the advertising strategy according to the advertising effect and the willingness of the store owner, and can improve the advertising effect and the user experience at the same time.

[0290] It should be understood that different embodiments described above can be combined with each other. For example, Figure 6 The corresponding embodiments can be combined. For example, Figure 3 The corresponding embodiments can be combined. For example, Figure 6 The corresponding embodiments can be combined. For example, Figure 5 The corresponding embodiments can be combined.

[0291] It should be understood that the same or corresponding information in different embodiments described above can be referred to each other.

[0292] The device embodiments of the present application are described below, which can be used to execute the methods in the embodiments of the present application. For details not disclosed in the device embodiments of the present application, please refer to the above method embodiments of the present application.

[0293] Based on the above network architecture, please refer to Figure 10 , Figure 10 is a structural schematic diagram of a store situation determination device disclosed according to an embodiment of the present application. The store situation determination device can be applied to the computer device described above. As shown in Figure 10 , the store situation determination device can include:

[0294] The acquisition unit 1001 is configured to acquire a detection record of a first electronic device, the detection record of the first electronic device including M WIFI identifiers and M WIFI signal strengths, the M WIFI identifiers and the M WIFI signal strengths corresponding to each other, and M being an integer greater than 0;

[0295] The first determination unit 1002 is configured to determine a WIFI feature according to the M WIFI identifiers, the M WIFI signal strengths, a first WIFI identifier, and a WIFI identifier list, the first WIFI identifier being a WIFI identifier of a target store, the WIFI identifier list being a list of WIFI identifiers detected in the target store, and the WIFI identifier list including the first WIFI identifier.

[0296] The second determination unit 1003 is configured to determine a probability that a first object has been to the target store by using a target probability model according to the WIFI feature, the first object corresponding to the first electronic device.

[0297] The third determination unit 1004 is configured to determine a condition that the first object has been to the target store according to the probability that the first object has been to the target store.

[0298] In some embodiments, the WIFI signal strengths include K strength levels, K being an integer greater than 1.

[0299] The first determination unit 1002 is specifically configured to:

[0300] Determine WIFI identifiers in the M WIFI identifiers that belong to the WIFI identifier list, to obtain N WIFI identifiers, N being an integer less than or equal to M.

[0301] Determine a detection feature according to detection probabilities corresponding to the N WIFI identifiers.

[0302] Determine a strength level corresponding to each of the N WIFI signal strengths according to the K strength levels, to obtain current strength levels corresponding to the N WIFI identifiers, the N WIFI signal strengths being N WIFI signal strengths corresponding to the N WIFI identifiers in the M WIFI signal strengths.

[0303] Determine a strength feature according to strength probabilities corresponding to the current strength levels corresponding to the N WIFI identifiers and the first WIFI identifier.

[0304] The second determination unit 1003 is specifically configured to determine the probability that the first object has been to the target store by using the target probability model according to the detection feature and the strength feature.

[0305] In some embodiments, the first determination unit 1002 determines the detection feature according to the detection probabilities corresponding to the N WIFI identifiers, including:

[0306] determining a sum of the N WIFI identifier corresponding detection probabilities to obtain a first feature;

[0307] determining an average of the N WIFI identifier corresponding detection probabilities to obtain a second feature;

[0308] determining a maximum of the N WIFI identifier corresponding detection probabilities to obtain a third feature;

[0309] determining the detection feature according to at least one of the first feature, the second feature and the third feature.

[0310] In some embodiments, the first determining unit 1002 determines the intensity feature according to the N WIFI identifier corresponding current intensity level corresponding intensity probability and the first WIFI identifier, including:

[0311] determining a sum of the N WIFI identifier corresponding current intensity level corresponding intensity probability to obtain a fourth feature;

[0312] determining an average of the N WIFI identifier corresponding current intensity level corresponding intensity probability to obtain a fifth feature;

[0313] determining a maximum of the N WIFI identifier corresponding current intensity level corresponding intensity probability to obtain a sixth feature;

[0314] determining the WIFI signal intensity of the target store according to the N WIFI signal intensity and the first WIFI identifier to obtain a seventh feature;

[0315] determining the intensity feature according to at least one of the fourth feature, the fifth feature and the sixth feature, and the seventh feature.

[0316] In some embodiments, the acquisition unit 1001 is further configured to acquire training data, the training data including a plurality of electronic device detection records and a plurality of electronic device corresponding object to the target store label;

[0317] The first determining unit 1002 is further configured to determine the detection feature and the intensity feature corresponding to the second electronic device according to the detection record of the second electronic device, the first WIFI identifier and the WIFI identifier list, the second electronic device being any electronic device in the plurality of electronic devices;

[0318] The second determining unit 1003 is further configured to determine the predicted probability of the second object to the target store using the initial probability model according to the detection feature and the intensity feature corresponding to the second electronic device, the second object being the object corresponding to the second electronic device;

[0319] The store situation determining apparatus can further include:

[0320] The fourth determining unit is configured to determine a loss value according to the predicted probability of the second object to the target store and the label.

[0321] The optimization unit is configured to optimize parameters of the initial probability model according to the loss value to obtain a target probability model.

[0322] In some embodiments, the store situation determining apparatus can further include a statistics unit, which is specifically configured to:

[0323] determine a total number of times of the object to the store according to the labels corresponding to the plurality of electronic devices;

[0324] determine a first number of times of the object to the target store and detecting the second WIFI label according to the detection records of the plurality of electronic devices and the labels of the plurality of electronic devices, the second WIFI label being any WIFI label in the WIFI label list;

[0325] determine a second number of times of the object to the target store and detecting a target intensity level corresponding to the second WIFI label according to the detection records of the plurality of electronic devices and the labels of the plurality of electronic devices, the target intensity level being any intensity level in the K intensity levels;

[0326] determine a detection probability corresponding to the second WIFI label according to the first number of times and the total number of times of the object to the store;

[0327] determine an intensity probability corresponding to the target intensity level corresponding to the second WIFI label according to the second number of times and the total number of times of the object to the store.

[0328] In some embodiments, the third determining unit 1004 is specifically configured to:

[0329] determine that the first object has been to the target store when the probability of the first object to the target store is greater than or equal to a probability threshold;

[0330] determine that the first object has not been to the target store when the probability of the first object to the target store is less than the probability threshold.

[0331] In some embodiments, the store situation determining apparatus can further include:

[0332] The fifth determining unit is configured to determine a store rate of the first object to the target store according to the situation of the first object to the target store;

[0333] The fifth determining unit is further configured to determine the target information according to the store rate of the first object to the target store;

[0334] The sending unit is configured to send the target information to the first electronic device.

[0335] The specific working processes of the acquisition unit 1001, the first determination unit 1002, the second determination unit 1003, the third determination unit 1004, the fourth determination unit, the optimization unit, the fifth determination unit, and the sending unit can refer to the corresponding processes in the foregoing method embodiments, and details are not described herein.

[0336] Please refer to Figure 11 , Figure 11 is a structural schematic diagram of a computer system of a computer device.

[0337] It should be noted that Figure 11 The computer system of the computer device shown is only an example, and should not impose any limitation on the functions and use range of the embodiments of the present application. The computer device can be used to execute the in-store situation determination method provided by the present application.

[0338] As Figure 11 shown, the computer system includes a central processing unit (CPU) 1101, which can perform various appropriate actions and processes, for example, execute the method in the foregoing embodiments, according to a program stored in a read-only memory (ROM) 1102 or a program loaded from a storage portion 1108 into a random access memory (RAM) 1103. In the RAM 1103, various programs and data required for system operation are also stored. The CPU 1101, the ROM 1102, and the RAM 1103 are connected to each other through a bus 1104. An input / output (I / O) interface 1105 is also connected to the bus 1104.

[0339] The following components are connected to the I / O interface 1105: an input portion 1106 including a keyboard, a mouse, and the like; an output portion 1107 including, for example, a cathode ray tube (CRT), a liquid crystal display (LCD), and the like, and a speaker, and the like; a storage portion 1108 including a hard disk, and the like; and a communication portion 1109 including a network interface card such as a LAN (Local Area Network) card, a modem, and the like. The communication portion 1109 performs communication processing via a network such as the Internet. A drive 1110 is also connected to the I / O interface 1105 as necessary. A removable recording medium 1111 such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, and the like is attached to the drive 1110 as necessary, so that a computer program read therefrom is installed in the storage portion 1108 as necessary.

[0340] In particular, according to embodiments of the present application, the processes described above with reference to the flowcharts can be implemented as a computer software program. For example, embodiments of the present application include a computer program product comprising a computer program carried on a computer readable medium, the computer program containing program code for executing the methods illustrated by the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network by the communication section 1109, and / or installed from the detachable medium 1111. When the computer program is executed by the central processing unit (CPU) 1101, various functions defined in the system of the present application are executed.

[0341] It should be noted that the computer readable medium shown in embodiments of the present application can be a computer readable signal medium or a computer readable storage medium or any combination of the two. The computer readable storage medium may, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or apparatus, or any combination of the above. More specific examples of the computer readable storage medium can include, but are not limited to, an electrical connection having one or more wires, a portable computer diskette, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM), a flash memory, an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present application, the computer readable storage medium can be any tangible medium that contains or stores a program that can be used by or in connection with an instruction execution system, apparatus or device. In the present application, the computer readable signal medium can include a data signal carried in a baseband or as a part of a carrier wave, which carries computer readable program code. Such a propagated data signal can take many forms, including but not limited to, an electromagnetic signal, an optical signal or any suitable combination of the above. The computer readable signal medium can also be any computer readable medium that can send, propagate or transfer a program for use by or in connection with an instruction execution system, apparatus or device. The program code contained on the computer readable medium can be transmitted by any suitable medium, including but not limited to wireless, wired, optical, electromagnetic or any suitable combination of the above.

[0342] The flowcharts and block diagrams in the drawings illustrate the architecture, functionality, and operation of possible implementations of various embodiments of the present application. In this regard, each block in the flowcharts and block diagrams can represent a module, a segment, or a portion of code, which comprises one or more executable instructions for implementing the specified logical functions. It should also be noted that in some alternative implementations, the functions noted in the blocks can occur out of the order noted in the figures. For example, two blocks noted in succession can in fact be executed substantially concurrently or can sometimes be executed in reverse order, depending on the functionality involved. It will also be noted that each block of the block diagrams and / or flowchart illustrations, and combinations thereof, can be implemented by special purpose hardware-based systems that perform the specified functions or operations, or combinations of special purpose hardware and computer instructions.

[0343] The units described in the embodiments of the present application can be implemented by software, or by hardware, or by a combination of software and hardware. The units described may

[0344] As another aspect, the present application also provides a computer readable storage medium, which can be included in the computer device described in the above embodiments, or can exist separately and not be assembled into the computer device. The computer readable storage medium carries computer readable instructions, which, when executed by a processor, implement the method in any of the above embodiments.

[0345] In the embodiments of the present application, the term "module" or "unit" refers to a computer program or a part of a computer program with a predetermined function, and works with other related parts to achieve a predetermined target, and can be implemented entirely or partially by using software, hardware (such as a processing circuit or a memory), or a combination thereof, and similarly, one processor (or multiple processors or memories) can be used to implement one or more modules or units. In addition, each module or unit can be a whole module or unit of the function of the module or unit, or a part of the module or unit.

[0346] According to an aspect of the embodiments of the present application, a computer program product or computer program is provided, which includes computer instructions stored in a computer readable storage medium. The processor of the computer device reads the computer instructions from the computer readable storage medium, and the processor executes the computer instructions, so that the computer device executes the method in any of the above embodiments.

[0347] It should be noted that, although several modules or units for a device for action execution are mentioned in the above detailed description, such division into modules or units is not mandatory. Indeed, according to an embodiment of the application, the features and functionalities of two or more modules or units described above can be embodied in one module or unit. Conversely, the features and functionalities of one module or unit described above can be further divided into several modules or units embodied by.

[0348] Those skilled in the art can easily understand, through the above description of the embodiments, that the example embodiments described herein can be implemented by software, or by software in combination with necessary hardware. Therefore, the technical solutions according to the embodiments of the present application can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, a U disk, a mobile hard disk, etc.) or on a network, and includes a number of instructions to make a computing device (which can be a personal computer, a server, a touch terminal, or a network device, etc.) execute the methods according to the embodiments of the present application.

[0349] Other embodiments of the present application will be apparent to those skilled in the art from consideration of the specification and practice of the embodiments disclosed herein. The present application is intended to cover any variations, uses, or adaptations of the application following, in general, the principles of the application and including such

[0350] It should be understood that the application is not limited to the precise construction that has been described above and shown in the accompanying drawings, and that various modifications and changes can be made by those skilled in the art without departing from the scope of the application. The scope of the application should only be limited by the appended claims.

Claims

1. A store visit situation determination method characterized by comprising: The method comprises: obtaining a detection record of a first electronic device, the detection record comprising M WIFI identifiers and M WIFI signal strengths, the M WIFI identifiers and the M WIFI signal strengths corresponding one by one, M being an integer greater than 0; determining a WIFI feature according to the M WIFI identifiers, the M WIFI signal strengths, a first WIFI identifier and a WIFI identifier list, the first WIFI identifier being a WIFI identifier of a target store, the WIFI identifier list being a list of WIFI identifiers detected in the target store, the WIFI identifier list comprising the first WIFI identifier; determining a probability that a first object has been to the target store using a target probability model according to the WIFI feature, the first object corresponding to the first electronic device; determining a condition that the first object has been to the target store according to the probability that the first object has been to the target store.

2. The method of claim 1, wherein, The WIFI signal strength comprises K strength levels, K being an integer greater than 1; the determination of the WIFI feature according to the M WIFI identifiers, the M WIFI signal strengths, the first WIFI identifier and the WIFI identifier list comprises: determining WIFI identifiers in the M WIFI identifiers that belong to the WIFI identifier list to obtain N WIFI identifiers, N being an integer less than or equal to M; determining a detection feature according to detection probabilities corresponding to the N WIFI identifiers; determining a strength level corresponding to each of N WIFI signal strengths according to the K strength levels to obtain current strength levels corresponding to the N WIFI identifiers, the N WIFI signal strengths being WIFI signal strengths corresponding to the N WIFI identifiers in the M WIFI signal strengths; determining a strength feature according to strength probabilities corresponding to the current strength levels of the N WIFI identifiers and the first WIFI identifier; the determination of the probability that the first object has been to the target store using the target probability model according to the WIFI feature comprises: determining the probability that the first object has been to the target store using the target probability model according to the detection feature and the strength feature.

3. The method of claim 2, wherein, the determination of the detection feature according to the detection probabilities corresponding to the N WIFI identifiers comprises: determining a sum of the detection probabilities corresponding to the N WIFI identifiers to obtain a first feature; determining an average of the detection probabilities corresponding to the N WIFI identifiers to obtain a second feature; determining a maximum value in the detection probabilities corresponding to the N WIFI identifiers to obtain a third feature; determining the detection feature according to at least one of the first feature, the second feature and the third feature.

4. The method of claim 2, wherein, the determination of the strength feature according to the strength probabilities corresponding to the current strength levels of the N WIFI identifiers and the first WIFI identifier comprises: determining a sum of the strength probabilities corresponding to the current strength levels of the N WIFI identifiers to obtain a fourth feature; determining an average of the strength probabilities corresponding to the current strength levels of the N WIFI identifiers to obtain a fifth feature; determining a maximum value in the strength probabilities corresponding to the current strength levels corresponding to the N WIFI identifiers, to obtain a sixth feature; determining a WIFI signal strength of the target store according to the N WIFI signal strengths and the first WIFI identifier, to obtain a seventh feature; determining a strength feature according to at least one of the fourth feature, the fifth feature and the sixth feature, and the seventh feature.

5. The method of claim 2, wherein, The method further comprises: obtaining training data, the training data comprising detection records of a plurality of electronic devices and labels of objects corresponding to the plurality of electronic devices visiting the target store; determining a detection feature and a strength feature corresponding to a second electronic device according to the detection records of the second electronic device, the first WIFI identifier and the WIFI identifier list, the second electronic device being any electronic device in the plurality of electronic devices; determining a predicted probability of a second object visiting the target store according to the detection feature and the strength feature corresponding to the second electronic device, the second object being an object corresponding to the second electronic device; determining a loss value according to the predicted probability of the second object visiting the target store and the label; optimizing parameters of an initial probability model according to the loss value, to obtain the target probability model.

6. The method of claim 5, wherein, The method further comprises: determining a total number of times of objects visiting the store according to the labels corresponding to the plurality of electronic devices; determining a first number of times of objects visiting the target store and detecting a second WIFI identifier according to the detection records of the plurality of electronic devices and the labels of the plurality of electronic devices, the second WIFI identifier being any WIFI identifier in the WIFI identifier list; determining a second number of times of objects visiting the target store and detecting a target strength level corresponding to the second WIFI identifier according to the detection records of the plurality of electronic devices and the labels of the plurality of electronic devices, the target strength level being any strength level in the K strength levels; determining a detection probability corresponding to the second WIFI identifier according to the first number of times and the total number of times of objects visiting the store; determining a strength probability corresponding to the target strength level corresponding to the second WIFI identifier according to the second number of times and the total number of times of objects visiting the store.

7. The method according to any one of claims 1 to 6, characterized in that, The determining of the situation of the first object visiting the target store according to the probability of the first object visiting the target store comprises: determining that the first object visits the target store in a case where the probability of the first object visiting the target store is greater than or equal to a probability threshold value; determining that the first object does not visit the target store in a case where the probability of the first object visiting the target store is less than the probability threshold value.

8. The method according to any one of claims 1 to 6, characterized in that, The method further comprises: determining a store visiting rate of the first object to the target store according to the situation of the first object visiting the target store; determining target information according to the store visiting rate; sending the target information to the first electronic device.

9. A store visit determination device characterized by comprising: It comprises: An acquisition unit is configured to acquire a detection record of a first electronic device, the detection record comprising M WIFI identifiers and M WIFI signal strengths, the M WIFI identifiers and the M WIFI signal strengths corresponding to each other one by one, M being an integer greater than 0; A first determination unit is configured to determine a WIFI feature according to the M WIFI identifiers, the M WIFI signal strengths, a first WIFI identifier, and a WIFI identifier list, the first WIFI identifier being a WIFI identifier of a target store, the WIFI identifier list being a list of WIFI identifiers detected in the target store, and the WIFI identifier list comprising the first WIFI identifier; A second determination unit is configured to determine a probability that a first object has been to the target store according to the WIFI feature and using a target probability model, the first object corresponding to the first electronic device; A third determination unit is configured to determine a condition that the first object has been to the target store according to the probability that the first object has been to the target store.

10. A computer device, comprising: comprise: a processor; a memory, the memory having computer readable instructions stored thereon, the computer readable instructions, when executed by the processor, implementing the method of any one of claims 1-8.

11. A computer-readable storage medium having stored thereon computer-readable instructions, wherein, When the computer readable instructions are executed by the processor, the method of any one of claims 1-8 is implemented.

12. A computer program product comprising computer instructions, characterized in that, When the computer instructions are executed by the processor, the method of any one of claims 1-8 is implemented.

Images