Target object information identification method, device, electronic device and readable storage medium

Abstract

Embodiments of the present invention provide a method, device, electronic device and readable storage medium for identifying target object information. The method comprises: determining a current relative value according to the browsing frequency of a product to be tested within a unit time period, wherein the current relative value is the difference between the browsing frequency and a preset base number, and the preset base number is a negative number; obtaining a historical relative value of the product to be tested according to a historical browsing normal value corresponding to the product to be tested in the unit time period, wherein the historical relative value is the difference between the historical browsing normal value and the preset base number; and determining a target object information identification result of the product to be tested according to the current relative value and the historical relative value, thereby reducing the possibility that the target object information identification result fluctuates too much due to the historical browsing normal value being too small, and improving the accuracy and reliability of target object information identification.

Description

Technical Field

[0001] The present invention relates to the field of Internet technology, and in particular to a method, device, electronic device and readable storage medium for identifying target object information. Background Art

[0002] With the rapid development of e-commerce, e-commerce companies use a variety of marketing methods to promote products and increase attention. Due to various preferential promotions or other reasons, the attention of some products fluctuates to varying degrees in the short term. Once the attention suddenly increases, it is likely to face problems such as network congestion, insufficient inventory or shortage of logistics resources. In order to assist in abnormal operation response and inventory management, it is necessary to identify the target object information whose attention suddenly exceeds its usual attention, so that when the target object information with a sudden increase in attention is identified, the abnormal operation response plan and inventory management plan for the target object information can be adjusted to allocate more resources to the target object information.

[0003] The existing technology usually uses the number of views per unit time as a measure of the degree of attention paid to a product. A commonly used method for identifying a product is to count the historical normal values ​​of the number of views per unit time of the product, and when the current value of the number of views per unit time of the product reaches a preset multiple of the historical normal value of the number of views per unit time, the product is determined as target object information.

[0004] During the research and development process, the inventors found that there are at least the following problems in the prior art: there is irrational allocation of resources due to misidentification of target object information, and the existing target object information identification method has low reliability. Summary of the invention

[0005] The embodiments of the present invention provide a method, device, electronic device and readable storage medium for identifying target object information, which improve the reliability of target object information identification.

[0006] According to a first aspect of the present invention, there is provided a method for identifying target object information, comprising:

[0007] Determine a current relative value according to the browsing frequency of the commodity to be tested within a unit time, wherein the current relative value is a difference between the browsing frequency and a preset base number, and the preset base number is a negative number;

[0008] According to the historical browsing normal value of the commodity to be tested corresponding to the unit time length, the historical relative value of the commodity to be tested is obtained, where the historical relative value is the difference between the historical browsing normal value and the preset base number;

[0009] The target object information recognition result of the commodity to be tested is determined according to the current relative value and the historical relative value.

[0010] Optionally, in a possible implementation manner of the first aspect, determining the target object information recognition result of the commodity to be tested according to the current relative value and the historical relative value includes:

[0011] Determine the evaluation value of the commodity to be tested in the unit time according to the current relative value and the historical relative value;

[0012] If the evaluation value of the commodity to be tested meets a preset condition within a preset time period, the commodity to be tested is determined to be target object information.

[0013] Optionally, in another possible implementation manner of the first aspect, if the evaluation value of the commodity to be tested meets a preset condition within a preset time period, determining that the commodity to be tested is the target object information includes:

[0014] If the evaluation value obtained by the commodity to be tested in one or more of the unit time lengths within the preset time period is greater than 0, the commodity to be tested is determined to be target object information.

[0015] Optionally, in another possible implementation manner of the first aspect, determining the evaluation value of the commodity to be tested in the unit time according to the current relative value and the historical relative value includes:

[0016] Determine the ratio of the current relative value to the historical relative value as an evaluation variable;

[0017] Determining whether the evaluation variable is greater than a preset evaluation threshold;

[0018] If yes, the difference between the evaluation variable and the evaluation threshold is used as the evaluation value;

[0019] If not, 0 is used as the evaluation value.

[0020] Optionally, in another possible implementation manner of the first aspect, before obtaining the historical relative value of the commodity to be tested, the method further includes:

[0021] The historical browsing normal value corresponding to the tested product in the unit time t is obtained according to the following formula 1:

[0022] h t =α×h t-1 +(1-α)×n t

[0023] Among them, h t is the historical browsing normal value corresponding to the unit time length, h t-1 is the historical browsing normal value corresponding to the previous unit time, n t is the current relative value, and α is the preset attenuation coefficient.

[0024] Optionally, in another possible implementation manner of the first aspect, before determining whether the evaluation variable is greater than a preset evaluation threshold, the method further includes:

[0025] The evaluation threshold is determined according to the preset time period and / or the business information of the commodity to be tested within the preset time period.

[0026] Optionally, in another possible implementation manner of the first aspect, before determining the current relative value according to the browsing frequency of the commodity to be tested within the unit time, the method further includes:

[0027] The unit time length is determined according to a preset time period of the commodity to be tested and / or business information of the commodity to be tested within the preset time period.

[0028] According to a second aspect of the present invention, there is provided a target object information recognition device, comprising:

[0029] A sampling module, used to determine a current relative value according to the browsing frequency of the tested product within a unit time, wherein the current relative value is a difference between the browsing frequency and a preset base number, and the preset base number is a negative number;

[0030] A calculation module, configured to obtain a historical relative value of the commodity to be tested according to the historical browsing normal value of the commodity to be tested corresponding to the unit time length, wherein the historical relative value is a difference between the historical browsing normal value and the preset base number;

[0031] The identification module is used to determine the target object information identification result of the commodity to be tested according to the current relative value and the historical relative value.

[0032] According to a third aspect of the present invention, there is provided an electronic device, comprising: a memory, a processor and a computer program; the computer program is stored in the memory, and the processor runs the computer program to execute the target object information recognition method of the first aspect of the present invention and various possible designs of the first aspect.

[0033] According to a fourth aspect of the present invention, a readable storage medium is provided, in which a computer program is stored. When the computer program is executed by a processor, it is used to implement the target object information identification method of the first aspect of the present invention and various possible designs of the first aspect.

[0034] Embodiments of the present invention provide a method, device, electronic device and readable storage medium for identifying target object information. The method comprises: determining a current relative value according to the browsing frequency of a product to be tested within a unit time period, wherein the current relative value is the difference between the browsing frequency and a preset base number, and the preset base number is a negative number; obtaining a historical relative value of the product to be tested according to a historical browsing normal value corresponding to the product to be tested in the unit time period, wherein the historical relative value is the difference between the historical browsing normal value and the preset base number; and determining a target object information identification result of the product to be tested according to the current relative value and the historical relative value, thereby reducing the possibility that the target object information identification result fluctuates too much due to the historical browsing normal value being too small, and improving the accuracy and reliability of target object information identification. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] Figure 1 This is a schematic diagram of an application scenario provided by an embodiment of the present invention;

[0036] Figure 2 It is a schematic diagram of a target object information identification method provided by an embodiment of the present invention;

[0037] Figure 3 This is a schematic diagram of a change curve of browsing frequency, historical browsing normal value and evaluation value provided by an embodiment of the present invention;

[0038] Figure 4 This is another schematic diagram of a change curve of browsing frequency, historical browsing normal value and evaluation value provided by an embodiment of the present invention;

[0039] Figure 5 It is a schematic diagram of the structure of a target object information identification device provided by an embodiment of the present invention;

[0040] Figure 6 It is a schematic diagram of the hardware structure of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0041] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0042] The terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the numbers used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in sequences other than those illustrated or described herein.

[0043] It should be understood that in various embodiments of the present invention, the size of the sequence number of each process does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

[0044] It should be understood that in the present invention, "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or apparatus comprising a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to these processes, methods, products or apparatuses.

[0045] It should be understood that in the present invention, "plurality" refers to two or more than two. "And / or" is merely a description of the association relationship of associated objects, indicating that three relationships may exist. For example, and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. The character " / " generally indicates that the objects associated before and after are in an "or" relationship. "Contains A, B and C", "Contains A, B, C" means that A, B, and C are all included, "Contains A, B or C" means that one of A, B, and C is included, and "Contains A, B and / or C" means that any one, any two, or any three of A, B, and C are included.

[0046] It should be understood that in the present invention, "B corresponding to A", "B corresponding to A", "A corresponds to B" or "B corresponds to A" means that B is associated with A and B can be determined according to A. Determining B according to A does not mean that B is determined only according to A, but B can also be determined according to A and / or other information.

[0047] Depending on the context, "if" as used herein may be interpreted as "when" or "when" or "in response to determining" or "in response to detecting."

[0048] The technical solution of the present invention is described in detail with specific embodiments below. The following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described in detail in some embodiments.

[0049] See also Figure 1 , is a schematic diagram of an application scenario provided by an embodiment of the present invention. Figure 1The application scenario shown can be understood as an e-commerce system, in which server 1 interacts with multiple user terminals 2 through a network to perform data exchange. Server 1 displays information about the products to be tested that participate in the promotional business to the user holding the user terminal 2 in the form of a web page or an application program interface. Promotional businesses can be, for example, "Today's Offer", "New Product Offer", "Anniversary Promotion", "Limited Time Flash Sale", etc. The user clicks on the display interface of the user terminal 2 to enter the web page or sub-interface of the product to be tested and browse the information of the product to be tested. The target object information in this embodiment can be understood as a product with explosive product characteristics.

[0050] However, when the existing target object information recognition methods identify unpopular products, the historical normal value of the page views per unit time is usually small or close to 0. During the promotion period, a small increase in the current value of the page views per unit time can reach or even far exceed the historical normal value, thus causing misidentification of the target object information. In order to solve this problem, Figure 1 In the embodiment shown, server 1 collects browsing information of each product to be tested, obtains current relative values ​​and historical relative values ​​relative to a preset base, performs target object information identification in the following various embodiments, and obtains target object information identification results, thereby reducing the possibility of excessive fluctuations in target object information identification results due to excessively small historical browsing normal values, and improving the accuracy and reliability of target object information identification.

[0051] See also Figure 2 , is a flow chart of a target object information identification method provided by an embodiment of the present invention, Figure 2 The execution subject of the method shown can be software and / or hardware devices, for example Figure 1 Server 1 is shown. Figure 2 The method shown mainly includes steps S101 to S103, which are specifically as follows:

[0052] S101, determining a current relative value according to the browsing frequency of the commodity to be tested within a unit time, wherein the current relative value is a difference between the browsing frequency and a preset base number, and the preset base number is a negative number.

[0053] It can be to obtain the log information of all users, and then obtain the browsing frequency of the commodity to be tested within the unit time according to the log information. Optionally, before determining the current relative value according to the browsing frequency of the commodity to be tested within the unit time, the unit time can also be determined according to the preset time period of the commodity to be tested, and / or the business information of the commodity to be tested within the preset time period. It can be understood that short-term promotional activities such as "10-minute limited-time flash sale activities" usually have higher browsing volume than long-term promotional activities such as "today's discount", "new product listing discount", and "anniversary promotion". Optionally, the preset time period of the commodity to be tested can be obtained, for example, if the preset time period is 10 minutes and the browsing volume changes dramatically, the unit time can be determined as 30 seconds. Or for example, if the preset time period is 72 hours and the browsing volume changes relatively slowly, the unit time can be determined as 5 minutes or 1 hour. Optionally, the business information of the commodity to be tested can also be obtained, for example, if the business information is "10-minute limited-time flash sale activities" and the browsing volume changes dramatically, the unit time can be determined as 30 seconds. Or, for example, if the business information is "Today's Offer" and the page views change relatively slowly, the unit duration can be determined as 5 minutes. Optionally, the unit duration can be determined by combining the preset time period with the business information. The business information can be, for example, the promotion intensity level. The higher the promotion intensity level and the shorter the preset time period, the shorter the unit duration.

[0054] Browsing frequency refers to the number of views of the tested product within a unit time. After obtaining the browsing frequency, the difference between the browsing frequency and the preset base number is used as the current relative value, which can smooth the change in browsing frequency and reduce the possibility of misidentification of target object information.

[0055] S102, obtaining a historical relative value of the commodity to be tested according to the historical browsing normal value of the commodity to be tested corresponding to the unit time, wherein the historical relative value is a difference between the historical browsing normal value and the preset base number.

[0056] It can be to obtain the log information of all users, and then obtain the historical browsing normal value corresponding to the unit time length of the product to be tested based on the log information. Among them, the historical browsing normal value can be understood as the average browsing frequency of the preset time period before the unit time length, or the representative value of the browsing frequency of the preset time period before the unit time length. Due to the continuous change of browsing frequency, the historical browsing normal value corresponding to each unit time length may be different. The historical relative value can be understood as the difference between the historical browsing normal value and the preset base number.

[0057] S103: Determine a target object information recognition result of the commodity to be tested according to the current relative value and the historical relative value.

[0058] It can be understood that the evaluation value of the commodity to be tested in the unit time is first determined based on the current relative value and the historical relative value. The evaluation value can be understood as whether the commodity is the target object information and the degree of attention paid to the commodity. If the evaluation value of the commodity to be tested meets the preset conditions within the preset time period, the commodity to be tested is determined to be the target object information.

[0059] Optionally, the preset condition may be: if the evaluation value obtained for the commodity to be tested in one or more of the unit durations within a preset time period is greater than 0, the commodity to be tested is determined to be the target object information. The preset time period may be calculated based on the business information of the commodity to be tested participating in the promotional activity, or may be preset in the business information. In the example where the target object information is a commodity with explosive product characteristics, it can be understood that if the evaluation value detected in at least one unit duration is greater than 0 within the preset time period of 10 minutes of the "10-minute limited time flash sale activity", the commodity can be determined to be a commodity with explosive product characteristics. If cheating software is used to increase the number of views, a large number of browsing records may be suddenly generated within a period of time. In order to reduce the misidentification of the target object information caused by the interference browsing frequency generated in a certain time period, the preset condition may further be: if the evaluation value obtained for the commodity to be tested in multiple discontinuous unit durations within the preset time period is greater than 0, the commodity to be tested is determined to be the target object information, wherein the interval between the discontinuous unit durations is greater than the preset interval. For example, among the multiple unit durations with evaluation values ​​greater than 0, there are 8 intervals greater than 1 minute (preset interval), then the commodity to be tested is determined to be the target object information. Figure 3 , is a schematic diagram of a change curve of browsing frequency, historical browsing normal value and evaluation value provided by an embodiment of the present invention. After the promotion activity ends, the evaluation value curve may appear as follows: Figure 3 The case where the value is less than 0 is consistent with the user's unwillingness to buy the product at a high price after the promotion ends. The part of the evaluation value curve that is greater than 0 can be understood as the current relative value exceeding the historical relative value by a certain multiple within a preset time period, which is used to indicate that the product to be tested is the target object information.

[0060] Optionally, a specific method of determining the evaluation value of the commodity to be tested in the unit time period based on the current relative value and the historical relative value may be to calculate the evaluation value using the following formula (1).

[0061]

[0062] Among them, s t is the evaluation value; n t -d is the current relative value, h t-d is the historical relative value, d is the preset base, which is a negative value, and k is the evaluation threshold. Figure 3 The evaluation value curve shown is an evaluation value calculation method corresponding to the formula (1).

[0063] Optionally, another specific method of determining the evaluation value of the commodity to be tested in the unit time length according to the current relative value and the historical relative value may be: determining the ratio of the current relative value to the historical relative value as an evaluation variable; then judging whether the evaluation variable is greater than a preset evaluation threshold; if so, taking the difference between the evaluation variable and the evaluation threshold as the evaluation value; if not, taking 0 as the evaluation value. Optionally, the evaluation value may be calculated using the following formula (2).

[0064]

[0065] Among them, s t ′ is the evaluation value; n t -d is the current relative value, h t -d is the historical relative value, d is the preset base, the preset base is a negative value, and k is the evaluation threshold. Figure 4 , is another schematic diagram of a change curve of browsing frequency, historical browsing normal value and evaluation value provided by an embodiment of the present invention. Figure 4 The evaluation value curve shown is the evaluation value calculation method corresponding to formula (2). Figure 3 The difference is that the evaluation value cuts off the part of the evaluation value curve where it is less than 0.

[0066] Optionally, the browsing frequency of non-tested products within the unit time period may be used as the absolute value of the preset base number.

[0067] Optionally, before determining whether the evaluation variable is greater than a preset evaluation threshold, the evaluation threshold may be determined in at least three of the following ways:

[0068] An optional implementation is to determine the evaluation threshold according to the preset time period. For example, a preset time period-evaluation threshold mapping relationship set can be established in advance, and then the evaluation threshold is queried in the preset time period-evaluation threshold mapping relationship set according to the preset time period of the commodity to be tested. It can be understood that the shorter the preset time period, the higher the evaluation threshold can be, which improves the accuracy of target object information recognition.

[0069] Another optional implementation method is to determine the evaluation threshold value based on the business information of the commodity to be tested within the preset time period. For example, a business information-evaluation threshold mapping relationship set can be established in advance, and then the evaluation threshold value can be queried in the business information-evaluation threshold mapping relationship set based on the business information of the commodity to be tested participating in the promotional activities within the preset time period. It can be understood that the greater the promotion intensity indicated by the business information (more publicity or more discounts), the higher the evaluation threshold value can be, which improves the accuracy of target object information identification.

[0070] Another optional implementation is to determine the evaluation threshold according to the preset time period and the business information of the commodity to be tested within the preset time period. Combining the above two implementations, the preset time period and the business information are comprehensively considered to obtain the evaluation threshold, thereby improving the accuracy of target object information recognition.

[0071] The target object information identification method provided in the present embodiment determines a current relative value according to the browsing frequency of the commodity to be tested within a unit time, wherein the current relative value is the difference between the browsing frequency and a preset base number, and the preset base number is a negative number; obtains a historical relative value of the commodity to be tested according to a historical browsing normal value corresponding to the commodity to be tested in the unit time, wherein the historical relative value is the difference between the historical browsing normal value and the preset base number; determines a target object information identification result of the commodity to be tested according to the current relative value and the historical relative value, thereby reducing the possibility of excessive fluctuations in the target object information identification result due to too small a historical browsing normal value, and improving the accuracy and reliability of target object information identification.

[0072] Since the calculation of the historical browsing normal value in the prior art requires obtaining the average of the browsing frequency in the preset time period before the current unit time length, or selecting a representative value, it needs to rely on historical data and cannot achieve real-time calculation or offline calculation. In order to improve the calculation speed of the historical browsing normal value and thus improve the calculation efficiency of the historical relative value, the embodiment of the present invention introduces an attenuation coefficient in the calculation of the historical browsing normal value on the basis of the above embodiment. Specifically, before obtaining the historical relative value of the product to be tested, the historical browsing normal value corresponding to the product to be tested in the unit time length t can be obtained according to the following formula (3):

[0073] h t =α×h t-1 +(1-α)×n t Formula (3)

[0074] Among them, h t is the historical browsing normal value corresponding to the unit time length, h t-1 is the historical browsing normal value corresponding to the previous unit time, nt is the current relative value, and α is the preset attenuation coefficient.

[0075] The attenuation coefficient can be preset, such as 0.999, or it can be a preset time period, and / or a numerical mapping relationship between the business information of the product to be tested and the attenuation coefficient within the preset time period, and then the corresponding attenuation coefficient in the numerical mapping relationship is obtained according to the preset time period and / or business information. Due to the effect of the attenuation coefficient, the initial value has little effect on the subsequent historical browsing normal value. The historical browsing normal value h t The initial value of can be preset, for example, set to 1.

[0076] This embodiment introduces an attenuation coefficient in the calculation of the historical browsing normal value, establishes the relationship between the historical browsing normal value of the current unit time and the historical browsing normal value of the previous unit time, and obtains a method for quickly and in real time calculating the historical browsing normal value, thereby improving the calculation speed of the historical browsing normal value, thereby improving the calculation efficiency of the historical relative value, and further improving the speed and efficiency of target object information recognition.

[0077] See also Figure 5 , is a schematic diagram of the structure of a target object information identification device provided by an embodiment of the present invention. Figure 5 The target object information recognition device 50 shown mainly includes:

[0078] The sampling module 51 is used to determine a current relative value according to the browsing frequency of the commodity to be tested within a unit time, wherein the current relative value is a difference between the browsing frequency and a preset base number, and the preset base number is a negative number.

[0079] The calculation module 52 is used to obtain the historical relative value of the commodity under test according to the historical browsing normal value of the commodity under test corresponding to the unit time length, and the historical relative value is the difference between the historical browsing normal value and the preset base number.

[0080] The identification module 53 is used to determine the target object information identification result of the commodity to be tested according to the current relative value and the historical relative value.

[0081] Figure 5 The target object information identification device 50 of the embodiment shown can be used to perform Figure 2 The implementation principles and technical effects of the steps in the method embodiment shown are similar and will not be repeated here.

[0082] Optionally, the identification module 53 is used to:

[0083] The evaluation value of the commodity to be tested in the unit time is determined according to the current relative value and the historical relative value; if the evaluation value of the commodity to be tested meets a preset condition within a preset time period, the commodity to be tested is determined to be target object information.

[0084] Optionally, the identification module 53 is specifically used for:

[0085] If the evaluation value obtained by the commodity to be tested in one or more of the unit time lengths within the preset time period is greater than 0, the commodity to be tested is determined to be target object information.

[0086] Optionally, the identification module 53 is specifically used to: determine the ratio of the current relative value to the historical relative value as an evaluation variable;

[0087] Determine whether the evaluation variable is greater than a preset evaluation threshold; if so, take the difference between the evaluation variable and the evaluation threshold as the evaluation value; if not, take 0 as the evaluation value.

[0088] The calculation module 52, before obtaining the historical relative value of the commodity to be tested, is further used to:

[0089] The historical browsing normal value corresponding to the tested product in the unit time t is obtained according to the following formula (3):

[0090] h t =α×h t-1 +(1-α)×n t Formula (3)

[0091] Among them, h t is the historical browsing normal value corresponding to the unit time length, h t-1 is the historical browsing normal value corresponding to the previous unit time, n t is the current relative value, and α is the preset attenuation coefficient.

[0092] Optionally, before determining whether the evaluation variable is greater than a preset evaluation threshold, the identification module 53 is further configured to:

[0093] The evaluation threshold is determined according to the preset time period and / or the business information of the commodity to be tested within the preset time period.

[0094] Optionally, before determining the current relative value according to the browsing frequency of the commodity to be tested within a unit time, the sampling module 51 is further configured to:

[0095] The unit time length is determined according to a preset time period of the commodity to be tested and / or business information of the commodity to be tested within the preset time period.

[0096] See also Figure 6 , is a schematic diagram of the hardware structure of an electronic device provided by an embodiment of the present invention, the electronic device 60 includes: a memory 62, a processor 61 and a computer program; wherein,

[0097] The memory 62 is used to store the computer program, and the memory may also be a flash memory. The computer program is, for example, an application program, a functional module, etc. for implementing the above method.

[0098] The processor 61 is used to execute the computer program stored in the memory to implement each step in the above target object information recognition method. For details, please refer to the relevant description in the above method embodiment.

[0099] Optionally, the memory 62 may be independent or integrated with the processor 61 .

[0100] When the memory 62 is a device independent of the processor 61, the electronic device 60 may further include:

[0101] The bus 63 is used to connect the memory 62 and the processor 61 .

[0102] The specific implementation of the above electronic device may be implemented by a server or by a terminal, which is not limited in the embodiment of the present invention.

[0103] The present invention also provides a readable storage medium, in which a computer program is stored. When the computer program is executed by a processor, it is used to implement the target object information identification method provided by the various embodiments described above.

[0104] Among them, the readable storage medium can be a computer storage medium or a communication medium. The communication medium includes any medium that facilitates the transmission of a computer program from one place to another. The computer storage medium can be any available medium that can be accessed by a general or special-purpose computer. For example, a readable storage medium is coupled to a processor so that the processor can read information from the readable storage medium and write information to the readable storage medium. Of course, the readable storage medium can also be a component of the processor. The processor and the readable storage medium can be located in an application-specific integrated circuit (Application Specific Integrated Circuits, abbreviated as: ASIC). In addition, the ASIC can be located in a user device. Of course, the processor and the readable storage medium can also exist in a communication device as discrete components.

[0105] The present invention also provides a program product, which includes an execution instruction, which is stored in a readable storage medium. At least one processor of a device can read the execution instruction from the readable storage medium, and at least one processor executes the execution instruction so that the device implements the target object information recognition method provided by the various embodiments described above.

[0106] In the above-mentioned embodiment of the electronic device, it should be understood that the processor can be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), etc. The general-purpose processor can be a microprocessor or any conventional processor. The steps of the method disclosed in the present invention can be directly embodied as being executed by a hardware processor, or can be executed by a combination of hardware and software modules in the processor.

[0107] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or replace some or all of the technical features therein by equivalents. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for identifying target object information, characterized in that: include: Determine a current relative value according to the browsing frequency of the commodity to be tested within a unit time, wherein the current relative value is a difference between the browsing frequency and a preset base number, and the preset base number is a negative number; The historical browsing normal value corresponding to the product to be tested in the unit time is obtained according to the following formula: h t =α×h t-1 +(1-a)×n t Among them, t is the unit time length, h t is the historical browsing normal value corresponding to the unit time length, h t-1 is the historical browsing normal value corresponding to the previous unit time, n t is the current relative value, and α is a preset attenuation coefficient; According to the historical browsing normal value of the commodity to be tested corresponding to the unit time length, the historical relative value of the commodity to be tested is obtained, where the historical relative value is the difference between the historical browsing normal value and the preset base number; The target object information recognition result of the commodity to be tested is determined according to the current relative value and the historical relative value.

2. The method according to claim 1, characterized in that The step of determining the target object information recognition result of the commodity to be tested according to the current relative value and the historical relative value includes: Determine the evaluation value of the commodity to be tested in the unit time according to the current relative value and the historical relative value; If the evaluation value of the commodity to be tested meets a preset condition within a preset time period, the commodity to be tested is determined to be target object information.

3. The method according to claim 2, characterized in that If the evaluation value of the commodity to be tested meets a preset condition within a preset time period, determining that the commodity to be tested is the target object information includes: If the evaluation value obtained by the commodity to be tested in one or more of the unit time lengths within the preset time period is greater than 0, the commodity to be tested is determined to be target object information.

4. The method according to claim 2, characterized in that: The determining, according to the current relative value and the historical relative value, the evaluation value of the commodity to be tested in the unit time period includes: Determine the ratio of the current relative value to the historical relative value as an evaluation variable; Determining whether the evaluation variable is greater than a preset evaluation threshold; If yes, the difference between the evaluation variable and the evaluation threshold is used as the evaluation value; If not, 0 is used as the evaluation value.

5. The method according to claim 4, characterized in that Before determining whether the evaluation variable is greater than a preset evaluation threshold, the method further includes: The evaluation threshold is determined according to the preset time period and / or the business information of the commodity to be tested within the preset time period.

6. The method according to any one of claims 1 to 5, characterized in that: Before determining the current relative value according to the browsing frequency of the commodity to be tested within the unit time, the method further includes: The unit time length is determined according to a preset time period of the commodity to be tested and / or business information of the commodity to be tested within the preset time period.

7. A target object information recognition device, characterized in that: include: A sampling module, used to determine a current relative value according to the browsing frequency of the tested product within a unit time, wherein the current relative value is a difference between the browsing frequency and a preset base number, and the preset base number is a negative number; A calculation module, configured to obtain a historical relative value of the commodity to be tested according to the historical browsing normal value of the commodity to be tested corresponding to the unit time length, wherein the historical relative value is a difference between the historical browsing normal value and the preset base number; An identification module, used to determine a target object information identification result of the commodity to be tested according to the current relative value and the historical relative value; The calculation module is further used to obtain the historical browsing normal value corresponding to the commodity to be tested in the unit time according to the following formula: h t =α×h t-1 +(1-a)×n t Among them, t is the unit time length, h t is the historical browsing normal value corresponding to the unit time length, h t-1 is the historical browsing normal value corresponding to the previous unit time, n t is the current relative value, and α is the preset attenuation coefficient.

8. An electronic device, characterized in that: include: Memory, processor and computer program; The computer program is stored in the memory, and the processor runs the computer program to execute the target object information recognition method according to any one of claims 1 to 6.

9. A readable storage medium, characterized in that: The readable storage medium stores a computer program, and when the computer program is executed by a processor, it is used to implement the target object information recognition method according to any one of claims 1 to 6.

Images